Arena Elo
Elo ratings from blind pairwise votes: a human is shown two anonymous outputs for the same prompt and picks the better one. The votes are collected and published by Arena — we ingest the ratings, we do not run the votes and we do not adjust them.
Arena Elo
Human preference rating from blind pairwise votes, ingested from Arena
Text ArenaText Arena (style controlled)
Text Arena
Elo from blind pairwise preference votes, collected and published by Arena. Higher is better. We ingest these ratings; we do not run the votes and we do not run our own evaluations.
The Known Good
Text Arena — full ranking
551 models rated
17,764,214 votes countedRatings captured 25 Oct 2026 Source: Arena
| # | Model | Creator | Elo | 95% CI | Votes | Known Good Index |
|---|---|---|---|---|---|---|
| 1 |
gemini-4-argon-high
|
1,533 | ±9 | 4,903 | — | |
| 1 |
Google: Gemini 4 Argon
|
1,526 | ±7 | 10,083 | — | |
| 2 |
Anthropic: Claude Opus 5.5
|
Anthropic | 1,516 | ±7 | 10,322 | — |
| 2 |
claude-opus-5.5-high
|
Anthropic | 1,516 | ±8 | 7,687 | — |
| 3 |
Anthropic: Claude Fable 5.1
|
Anthropic | 1,513 | ±6 | 16,343 | — |
| 3 |
claude-fable-5.1-max
|
Anthropic | 1,510 | ±6 | 14,121 | — |
| 4 |
claude-opus-5-max
|
Anthropic | 1,507 | ±5 | 31,907 | — |
| 5 |
muse-wonder-max
|
Meta | 1,504 | ±13 | 1,944 | — |
| 5 |
Anthropic: Claude Opus 5
|
Anthropic | 1,503 | ±4 | 71,020 | — |
| 3 |
claude-opus-4-6-thinking
|
Anthropic | 1,503 | ±4 | 72,425 | — |
| 6 |
claude-opus-5-high
|
Anthropic | 1,502 | ±4 | 65,663 | — |
| 7 |
claude-opus-4-6-high
|
Anthropic | 1,502 | ±3 | 80,827 | — |
| 7 |
Meta: Muse Wonder
|
Meta | 1,501 | ±8 | 6,001 | — |
| 8 |
gemini-3.8-flash-high
|
1,499 | ±5 | 35,670 | — | |
| 8 |
Google: Gemini 3.8 Flash
|
1,498 | ±4 | 43,997 | — | |
| 9 |
Anthropic: Claude Opus 4.6
|
Anthropic | 1,497 | ±3 | 88,206 | 86 |
| 10 |
Meta: Muse Spark 1.3
|
Meta | 1,491 | ±5 | 20,506 | — |
| 11 | Mi Xiaomi: MiMo-V2.6-Pro | Xiaomi | 1,491 | ±9 | 4,067 | — |
| 10 |
claude-fable-5-high
|
Anthropic | 1,491 | ±4 | 41,439 | — |
| 12 |
Anthropic: Claude Fable 5
|
Anthropic | 1,491 | ±4 | 44,253 | — |
| 7 |
claude-opus-4-7-thinking
|
Anthropic | 1,490 | ±4 | 60,222 | — |
| 12 |
muse-spark-1.3-max
|
Meta | 1,490 | ±6 | 16,731 | — |
| 13 |
claude-opus-4-7-high
|
Anthropic | 1,490 | ±4 | 65,125 | — |
| 14 |
Google: Gemini 3.7 Flash
|
1,490 | ±5 | 30,501 | — | |
| 14 |
gemini-3.7-flash-high
|
1,487 | ±5 | 26,328 | — | |
| 15 |
Qwen: Qwen3.8 Max
|
Alibaba | 1,484 | ±5 | 30,500 | — |
| 16 |
Anthropic: Claude Opus 4.7
|
Anthropic | 1,483 | ±4 | 66,183 | 90 |
| 18 |
gemini-3.5-flash-high
|
1,482 | ±4 | 48,486 | — | |
| 17 |
Meta: Muse Spark 1.2
|
Meta | 1,482 | ±7 | 10,470 | — |
| 18 |
Google: Gemini 3.5 Flash
|
1,482 | ±4 | 48,504 | 95 | |
| 19 |
Google: Gemini 3.1 Pro Preview
|
1,480 | ±3 | 130,819 | 93 | |
| 20 |
Google: Gemini 3.6 Flash
|
1,480 | ±4 | 36,102 | — | |
| 21 |
Gemini 3 Pro
|
1,479 | ±4 | 42,054 | — | |
| 21 |
gemini-3.6-flash-high
|
1,479 | ±4 | 36,122 | — | |
| 22 |
Meta: Muse Spark 1.1
|
Meta | 1,478 | ±4 | 46,121 | — |
| 23 |
gemini-3.5-flash-medium
|
1,477 | ±4 | 47,292 | — | |
| 24 |
kimi-k3-max
|
Moonshot AI | 1,476 | ±5 | 32,036 | — |
| 24 |
qwen3.7-max-preview
|
Alibaba | 1,475 | ±10 | 3,941 | — |
| 25 |
MoonshotAI: Kimi K3
|
Moonshot AI | 1,475 | ±4 | 35,379 | — |
| 26 |
muse-spark
|
Meta | 1,474 | ±6 | 14,147 | — |
| 27 |
Z.ai: GLM 5.3
|
Z.ai | 1,474 | ±5 | 25,144 | — |
| 28 |
Anthropic: Claude Sonnet 5.5
|
Anthropic | 1,473 | ±7 | 8,977 | — |
| 29 |
Z.ai: GLM 5.3 Flash
|
Z.ai | 1,472 | ±5 | 38,359 | — |
| 27 |
glm-5.3-max
|
Z.ai | 1,471 | ±5 | 22,543 | — |
| 28 |
gpt-5.5-high
|
OpenAI | 1,471 | ±4 | 69,401 | — |
| 30 |
claude-sonnet-5.5-xhigh
|
Anthropic | 1,470 | ±8 | 6,831 | — |
| 31 |
glm-5.2-max
|
Z.ai | 1,470 | ±4 | 49,820 | — |
| 31 |
qwen3.5-max-preview
|
Alibaba | 1,470 | ±5 | 22,601 | — |
| 32 |
Z.ai: GLM 5.2
|
Z.ai | 1,470 | ±4 | 52,283 | 91 |
| 33 |
gpt-5.4-high
|
OpenAI | 1,469 | ±4 | 64,776 | — |
| 34 |
ernie-5.1
|
Baidu | 1,468 | ±5 | 39,474 | — |
| 35 |
OpenAI: GPT-5.5
|
OpenAI | 1,467 | ±4 | 70,998 | 93 |
| 37 |
DeepSeek-V4.1-Flash-20260910 (Max)
|
DeepSeek | 1,464 | ±6 | 13,750 | — |
| 38 | Mi Xiaomi: MiMo-V2.5-Pro | Xiaomi | 1,464 | ±4 | 77,883 | — |
| 38 |
deepseek-v4.1-flash-max
|
DeepSeek | 1,463 | ±6 | 12,793 | — |
| 39 |
Z.ai: GLM 5.1
|
Z.ai | 1,463 | ±4 | 65,402 | 89 |
| 40 |
claude-opus-4-8-high
|
Anthropic | 1,461 | ±4 | 64,100 | — |
| 28 |
claude-opus-4-8-thinking
|
Anthropic | 1,460 | ±5 | 40,409 | — |
| 41 |
Anthropic: Claude Sonnet 4.6
|
Anthropic | 1,458 | ±3 | 70,953 | 80 |
| 42 |
Google: Gemini 2.5 Pro
|
1,458 | ±2 | 125,316 | 64 | |
| 43 |
OpenAI: GPT-5.6 Sol
|
OpenAI | 1,457 | ±4 | 42,713 | — |
| 43 |
gpt-5.6-sol-xhigh
|
OpenAI | 1,457 | ±4 | 40,442 | — |
| 44 |
MoonshotAI: Kimi K2.6
|
Moonshot AI | 1,455 | ±4 | 40,026 | 92 |
| 45 |
Qwen: Qwen3.7 Plus
|
Alibaba | 1,455 | ±4 | 42,058 | — |
| 46 |
Anthropic: Claude Opus 4.8
|
Anthropic | 1,454 | ±4 | 65,208 | — |
| 47 |
OpenAI: GPT-5.4
|
OpenAI | 1,452 | ±4 | 67,855 | 88 |
| 48 | Mi Xiaomi: MiMo-V2.6-Flash | Xiaomi | 1,452 | ±6 | 13,730 | — |
| 49 |
DeepSeek: DeepSeek V4 Pro 0423
|
DeepSeek | 1,451 | ±4 | 57,588 | 93 |
| 50 |
Anthropic: Claude Opus 4.5
|
Anthropic | 1,451 | ±3 | 72,850 | 71 |
| 51 |
Grok 4.20 Beta (Reasoning, 0309)
|
xAI | 1,451 | ±4 | 66,418 | — |
| 51 |
grok-4.20-beta-0309-reasoning
|
xAI | 1,451 | ±4 | 66,436 | — |
| 52 |
Grok 4.20 Multi-Agent Beta (0309)
|
xAI | 1,451 | ±4 | 64,928 | — |
| 52 |
grok-4.20-multi-agent-beta-0309
|
xAI | 1,450 | ±4 | 64,946 | — |
| 54 |
dola-seed-2.0-pro
|
ByteDance | 1,448 | ±3 | 79,130 | — |
| 53 | Az amazon-nova-experimental-chat-26-02-10 | Amazon | 1,448 | ±10 | 3,526 | — |
| 54 |
claude-opus-4-5-20251101-high-32k
|
Anthropic | 1,448 | ±4 | 37,509 | — |
| 55 |
OpenAI: GPT-5.6 Terra
|
OpenAI | 1,448 | ±4 | 46,470 | — |
| 57 |
SpaceXAI: Grok 4.5
|
xAI | 1,448 | ±4 | 39,880 | — |
| 57 |
gpt-6.1-sol-max
|
OpenAI | 1,448 | ±8 | 6,320 | — |
| 58 |
gpt-5.6-terra-xhigh
|
OpenAI | 1,447 | ±4 | 43,271 | — |
| 58 |
Qwen: Qwen3.6 Max Preview
|
Alibaba | 1,447 | ±8 | 5,423 | 89 |
| 43 |
claude-opus-4-5-20251101-thinking-32k
|
Anthropic | 1,447 | ±4 | 37,213 | — |
| 59 |
Z.ai: GLM 5
|
Z.ai | 1,446 | ±4 | 29,267 | 77 |
| 61 |
deepseek-v4-pro-high-20260813
|
DeepSeek | 1,446 | ±7 | 9,800 | — |
| 62 |
kimi-k2.5-thinking
|
Moonshot AI | 1,445 | ±3 | 74,759 | — |
| 61 |
MoonshotAI: Kimi K2.5
|
Moonshot AI | 1,445 | ±3 | 74,744 | — |
| 47 |
deepseek-v4-pro-thinking
|
DeepSeek | 1,445 | ±4 | 44,669 | — |
| 62 |
DeepSeek-V4-Pro Preview (High)
|
DeepSeek | 1,445 | ±4 | 54,896 | — |
| 63 |
deepseek-v4-pro-high-preview
|
DeepSeek | 1,445 | ±4 | 54,902 | — |
| 63 |
NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
|
NVIDIA | 1,445 | ±7 | 11,557 | — |
| 64 |
ERNIE 5.0 (0110)
|
Baidu | 1,445 | ±4 | 36,481 | — |
| 64 |
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
|
NVIDIA | 1,445 | ±7 | 11,567 | — |
| 65 |
grok-4.20-beta1
|
xAI | 1,445 | ±5 | 27,908 | — |
| 66 |
ernie-5.0-0110
|
Baidu | 1,445 | ±4 | 36,487 | — |
| 65 |
Grok 4.20 Beta 1
|
xAI | 1,445 | ±5 | 27,914 | — |
| 66 |
OpenAI: GPT-6.1 Sol
|
OpenAI | 1,444 | ±7 | 8,305 | — |
| 67 |
Google: Gemma 4 31B
|
1,443 | ±7 | 6,137 | — | |
| 68 |
gpt-5.1-high
|
OpenAI | 1,443 | ±4 | 41,651 | — |
| 69 |
gpt-6-astra-max
|
OpenAI | 1,443 | ±6 | 12,163 | — |
| 69 |
ERNIE-5.0-Preview (1022)
|
Baidu | 1,443 | ±6 | 9,805 | — |
| 70 |
gemini-3-flash
|
1,442 | ±3 | 90,998 | — | |
| 71 |
Anthropic: Claude Sonnet 5
|
Anthropic | 1,442 | ±4 | 51,784 | — |
| 71 |
ernie-5.0-preview-1203
|
Baidu | 1,442 | ±6 | 9,806 | — |
| 72 |
claude-sonnet-5-high
|
Anthropic | 1,442 | ±4 | 49,595 | — |
| 73 |
OpenAI: GPT-6 Astra
|
OpenAI | 1,442 | ±6 | 14,076 | — |
| 72 | TM Thinking Machines: Inkling | Thinking Machines | 1,442 | ±4 | 43,705 | — |
| 74 | St StepFun: Step 5 Preview | stepfun | 1,442 | ±7 | 9,792 | — |
| 75 |
Z.ai: GLM 4.6
|
Z.ai | 1,440 | ±4 | 35,818 | — |
| 76 |
Qwen: Qwen3.8 27B
|
Alibaba | 1,440 | ±5 | 26,238 | — |
| 77 |
qwen3-max-preview
|
Alibaba | 1,439 | ±5 | 27,367 | — |
| 78 |
gpt-5.2-chat-latest-20260210
|
OpenAI | 1,438 | ±4 | 35,999 | — |
| 78 |
OpenAI: GPT-5.2 Chat
|
OpenAI | 1,438 | ±4 | 35,982 | — |
| 80 |
Tencent: Hy3
|
Tencent | 1,438 | ±6 | 13,220 | — |
| 79 |
claude-sonnet-4-5-20250929
|
Anthropic | 1,438 | ±3 | 82,688 | 66 |
| 81 |
Qwen: Qwen3.5 397B A17B
|
Alibaba | 1,438 | ±3 | 96,206 | — |
| 82 |
Z.ai: GLM 5V Turbo
|
Z.ai | 1,438 | ±6 | 10,477 | — |
| 83 |
grok-4.1-thinking
|
xAI | 1,436 | ±3 | 66,509 | — |
| 83 |
Qwen: Qwen3.6 Plus
|
Alibaba | 1,436 | ±4 | 48,142 | 78 |
| 85 | Mi mimo-v2-pro | Xiaomi | 1,436 | ±5 | 25,435 | — |
| 86 |
grok-4.1
|
xAI | 1,436 | ±3 | 68,621 | — |
| 87 |
Z.ai: GLM 4.7
|
Z.ai | 1,435 | ±6 | 12,245 | 68 |
| 88 |
Google: Gemini 3.5 Flash Lite
|
1,435 | ±4 | 35,829 | — | |
| 88 |
claude-sonnet-4-5-20250929-high-32k
|
Anthropic | 1,435 | ±3 | 83,940 | — |
| 89 |
Anthropic: Claude Sonnet 4.5
|
Anthropic | 1,435 | ±3 | 83,906 | — |
| 90 |
Google: Gemma 4 26B A4B
|
1,434 | ±7 | 6,092 | — | |
| 73 |
claude-sonnet-4-5-20250929-thinking-32k
|
Anthropic | 1,433 | ±3 | 82,549 | — |
| 91 |
DeepSeek: DeepSeek V4 Flash 0423
|
DeepSeek | 1,432 | ±4 | 51,982 | — |
| 92 |
Mistral: Mistral Large 4
|
Mistral | 1,432 | ±6 | 10,331 | — |
| 93 |
MiniMax: MiniMax M3
|
MiniMax | 1,432 | ±4 | 67,030 | — |
| 94 |
OpenAI: GPT-5.6 Luna
|
OpenAI | 1,431 | ±4 | 41,426 | — |
| 93 |
gpt-5.6-luna-xhigh
|
OpenAI | 1,431 | ±4 | 41,109 | — |
| 95 |
Z.ai: GLM 4.5
|
Z.ai | 1,430 | ±5 | 23,791 | — |
| 96 |
ernie-5.0-preview-1022
|
Baidu | 1,430 | ±9 | 4,753 | — |
| 97 |
SpaceXAI: Grok 4.6
|
xAI | 1,430 | ±5 | 32,189 | — |
| 98 |
ChatGPT-4o Latest (20250326)
|
OpenAI | 1,428 | ±3 | 81,905 | — |
| 97 |
chatgpt-4o-latest-20250326
|
OpenAI | 1,428 | ±3 | 81,914 | — |
| 99 |
mistral-large-3
|
Mistral | 1,428 | ±3 | 86,928 | — |
| 100 | Mi Xiaomi: MiMo-V2.5 | Xiaomi | 1,428 | ±4 | 47,364 | — |
| 99 |
grok-4.6-high
|
xAI | 1,428 | ±5 | 28,965 | — |
| 101 |
DeepSeek: R1 0528
|
DeepSeek | 1,428 | ±6 | 18,167 | — |
| 102 | Me LongCat-Flash-Chat Exp (2602) | meituan | 1,427 | ±4 | 29,275 | — |
| 102 | Me longcat-flash-chat-2602-exp | meituan | 1,426 | ±4 | 29,291 | — |
| 103 | Re Reflection: Beam 1.0 501B A23B | reflection | 1,426 | ±9 | 4,237 | — |
| 104 |
Grok 3 Preview (02-24)
|
xAI | 1,425 | ±4 | 32,498 | — |
| 103 |
grok-3-preview-02-24
|
xAI | 1,425 | ±4 | 32,499 | — |
| 104 |
deepseek-v3.2-exp-thinking
|
DeepSeek | 1,425 | ±7 | 8,998 | — |
| 106 |
DeepSeek: DeepSeek V3.2
|
DeepSeek | 1,425 | ±3 | 48,090 | — |
| 106 |
deepseek-v4-flash-high-preview
|
DeepSeek | 1,424 | ±4 | 51,809 | — |
| 107 |
DeepSeek-V4-Flash Preview (High)
|
DeepSeek | 1,424 | ±4 | 51,781 | — |
| 108 |
Mistral: Mistral Medium 3.1
|
Mistral | 1,424 | ±3 | 95,285 | — |
| 85 |
deepseek-v4-flash-thinking
|
DeepSeek | 1,423 | ±4 | 46,445 | — |
| 109 | Mi mimo-v2-omni | Xiaomi | 1,423 | ±6 | 20,618 | — |
| 110 | Me longcat-flash-chat | meituan | 1,423 | ±6 | 11,166 | — |
| 111 |
OpenAI: GPT-5.1
|
OpenAI | 1,422 | ±4 | 44,419 | 73 |
| 112 |
DeepSeek: DeepSeek V3.2 Exp
|
DeepSeek | 1,422 | ±6 | 11,997 | — |
| 113 |
Mistral: Mistral Medium 3.5
|
Mistral | 1,421 | ±6 | 11,791 | — |
| 113 |
kimi-k2.5-instant
|
Moonshot AI | 1,420 | ±6 | 8,376 | — |
| 115 |
Qwen: Qwen3 VL 235B A22B Instruct
|
Alibaba | 1,420 | ±6 | 11,312 | — |
| 115 |
deepseek-v3.2-thinking
|
DeepSeek | 1,420 | ±4 | 42,071 | — |
| 117 |
DeepSeek: DeepSeek V3.1
|
DeepSeek | 1,420 | ±6 | 14,607 | — |
| 117 | Az amazon-nova-experimental-chat-12-10 | Amazon | 1,419 | ±9 | 3,733 | — |
| 120 |
gpt-5.5-instant
|
OpenAI | 1,419 | ±5 | 27,163 | — |
| 118 |
claude-opus-4-1-20250805-thinking-16k
|
Anthropic | 1,419 | ±3 | 49,542 | — |
| 122 |
Qwen3-235B-A22B-Instruct (2507)
|
Alibaba | 1,419 | ±3 | 98,096 | — |
| 120 |
deepseek-v3.1-terminus-thinking
|
DeepSeek | 1,419 | ±10 | 3,375 | — |
| 119 |
Qwen: Qwen3 235B A22B Instruct 2507
|
Alibaba | 1,419 | ±3 | 98,134 | — |
| 123 |
Anthropic: Claude Opus 4.1
|
Anthropic | 1,419 | ±3 | 77,211 | 49 |
| 124 |
Qwen: Qwen3.5-122B-A10B
|
Alibaba | 1,418 | ±4 | 29,716 | — |
| 125 |
gpt-4.5-preview
|
OpenAI | 1,417 | ±6 | 14,547 | 54 |
| 124 |
gpt-4.5-preview-2025-02-27
|
OpenAI | 1,417 | ±6 | 14,547 | — |
| 126 |
DeepSeek: DeepSeek V3.1 Terminus
|
DeepSeek | 1,417 | ±10 | 3,608 | — |
| 127 |
Qwen: Qwen3 Next 80B A3B Instruct
|
Alibaba | 1,417 | ±5 | 22,755 | — |
| 128 |
Google: Gemini 2.5 Flash
|
1,417 | ±2 | 125,462 | — | |
| 128 |
deepseek-v3.1-thinking
|
DeepSeek | 1,417 | ±7 | 11,459 | — |
| 129 |
gpt-5.2-high
|
OpenAI | 1,416 | ±4 | 49,655 | — |
| 131 |
Google: Gemini 3.1 Flash Lite Preview
|
1,416 | ±4 | 64,209 | — | |
| 132 | Az amazon-nova-experimental-chat (10-09) | Amazon | 1,415 | ±4 | 26,031 | — |
| 133 |
Qwen3-235B-A22B-Thinking (2507)
|
Alibaba | 1,415 | ±7 | 8,821 | — |
| 131 |
Qwen: Qwen3 235B A22B Thinking 2507
|
Alibaba | 1,415 | ±7 | 8,823 | — |
| 132 | Az amazon-nova-experimental-chat-11-10 | Amazon | 1,415 | ±4 | 26,039 | — |
| 134 |
kimi-k2-thinking-turbo
|
Moonshot AI | 1,414 | ±3 | 63,348 | — |
| 135 | TM Thinking Machines: Inkling Small | Thinking Machines | 1,413 | ±5 | 35,359 | — |
| 136 |
Qwen: Qwen3 Max
|
Alibaba | 1,413 | ±6 | 9,027 | — |
| 134 |
qwen3-max-2025-09-23
|
Alibaba | 1,413 | ±6 | 9,027 | — |
| 137 |
OpenAI: GPT-5.2
|
OpenAI | 1,412 | ±3 | 83,828 | 79 |
| 138 |
OpenAI: GPT-5.4 Mini
|
OpenAI | 1,412 | ±4 | 63,451 | — |
| 137 |
gpt-5.4-mini-high
|
OpenAI | 1,411 | ±4 | 63,449 | — |
| 139 |
grok-4-0709
|
xAI | 1,411 | ±4 | 39,679 | 67 |
| 140 | Mi mimo-v2-flash (non-thinking) | Xiaomi | 1,411 | ±3 | 48,069 | — |
| 141 |
OpenAI: o3
|
OpenAI | 1,410 | ±4 | 58,894 | 72 |
| 140 |
o3-2025-04-16
|
OpenAI | 1,410 | ±4 | 58,908 | — |
| 142 |
Qwen: Qwen3.5-27B
|
Alibaba | 1,409 | ±4 | 28,661 | — |
| 141 |
nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4
|
NVIDIA | 1,409 | ±12 | 2,523 | — |
| 143 |
Grok 4.1 Fast (Reasoning)
|
xAI | 1,408 | ±3 | 57,526 | — |
| 143 |
grok-4-1-fast-reasoning
|
xAI | 1,408 | ±3 | 57,541 | — |
| 144 |
grok-4-fast-chat
|
xAI | 1,407 | ±8 | 6,340 | — |
| 145 |
Gemini 2.5 Flash Preview (May 2025)
|
1,406 | ±4 | 32,982 | — | |
| 145 |
gemini-2.5-flash-preview-09-2025
|
1,406 | ±4 | 32,995 | — | |
| 146 |
OpenAI: GPT-5
|
OpenAI | 1,406 | ±4 | 31,712 | 77 |
| 146 |
gpt-5-high
|
OpenAI | 1,406 | ±4 | 31,722 | — |
| 147 |
hunyuan-vision-1.5-thinking
|
Tencent | 1,406 | ±12 | 2,168 | — |
| 148 |
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
|
NVIDIA | 1,405 | ±9 | 4,176 | — |
| 149 |
MiniMax: MiniMax M2.7
|
MiniMax | 1,405 | ±3 | 87,731 | — |
| 150 |
OpenAI: GPT-5 Chat
|
OpenAI | 1,403 | ±4 | 31,183 | — |
| 151 | St StepFun: Step 3.5 Flash | stepfun | 1,403 | ±4 | 60,329 | — |
| 151 |
hunyuan-hy3-preview
|
Tencent | 1,402 | ±7 | 6,879 | — |
| 152 |
Tencent: Hy3 preview
|
Tencent | 1,401 | ±7 | 6,875 | — |
| 153 |
Anthropic: Claude Haiku 5.5
|
Anthropic | 1,401 | ±8 | 6,080 | — |
| 154 |
Qwen: Qwen3 VL 235B A22B Thinking
|
Alibaba | 1,401 | ±7 | 7,855 | — |
| 155 |
Hunyuan T1 (20250711)
|
Tencent | 1,401 | ±9 | 4,595 | — |
| 153 |
grok-4.7-xhigh
|
xAI | 1,401 | ±6 | 11,591 | — |
| 154 |
hunyuan-t1-20250711
|
Tencent | 1,400 | ±9 | 4,595 | — |
| 155 |
grok-4-fast-reasoning
|
xAI | 1,400 | ±5 | 18,269 | — |
| 156 |
Grok 4 Fast (Non-Reasoning)
|
xAI | 1,400 | ±5 | 18,267 | — |
| 157 |
OpenAI: GPT-6 Sol
|
OpenAI | 1,398 | ±6 | 14,707 | — |
| 156 |
gpt-6-sol-max
|
OpenAI | 1,398 | ±6 | 12,466 | — |
| 158 |
SpaceXAI: Grok 4.7
|
xAI | 1,398 | ±6 | 14,693 | — |
| 159 |
Qwen: Qwen3.5-Flash
|
Alibaba | 1,397 | ±4 | 61,802 | — |
| 160 |
SpaceXAI: Grok 4.3
|
xAI | 1,397 | ±4 | 71,348 | — |
| 161 |
Anthropic: Claude Haiku 4.5
|
Anthropic | 1,397 | ±2 | 152,393 | — |
| 159 |
claude-haiku-4-5-20251001
|
Anthropic | 1,397 | ±2 | 149,199 | 67 |
| 160 | Az amazon-nova-experimental-chat-26-01-10 | Amazon | 1,396 | ±10 | 3,539 | — |
| 163 | Mi mimo-v2-flash (thinking) | Xiaomi | 1,395 | ±6 | 11,140 | — |
| 164 |
Qwen: Qwen3.5-35B-A3B
|
Alibaba | 1,395 | ±4 | 30,443 | — |
| 163 | Az amazon-nova-experimental-chat-10-20 | Amazon | 1,394 | ±6 | 11,626 | — |
| 166 |
Qwen: Qwen3 235B A22B
|
Alibaba | 1,393 | ±4 | 37,485 | — |
| 164 |
qwen3-235b-a22b-no-thinking
|
Alibaba | 1,393 | ±4 | 37,484 | — |
| 167 |
minimax-m2.1-preview
|
MiniMax | 1,392 | ±5 | 17,230 | — |
| 166 |
gpt-6-luna-max
|
OpenAI | 1,392 | ±5 | 49,617 | — |
| 168 |
OpenAI: GPT-6 Luna
|
OpenAI | 1,390 | ±4 | 72,504 | — |
| 169 |
muse-glimmer
|
Meta | 1,389 | ±10 | 3,889 | — |
| 170 |
OpenAI: GPT-5.3 Chat
|
OpenAI | 1,389 | ±4 | 34,324 | — |
| 171 |
Upstage: Solar Pro 4
|
Upstage | 1,388 | ±5 | 24,453 | — |
| 169 |
solar-pro4
|
Upstage | 1,387 | ±5 | 21,281 | — |
| 170 |
Qwen: Qwen3 30B A3B Instruct 2507
|
Alibaba | 1,384 | ±5 | 23,322 | — |
| 172 |
Qwen3-30B-A3B-Instruct (2507)
|
Alibaba | 1,384 | ±5 | 23,306 | — |
| 173 |
Z.ai: GLM 4.5 Air
|
Z.ai | 1,384 | ±4 | 30,646 | — |
| 174 |
OpenAI: GPT-4.1
|
OpenAI | 1,383 | ±4 | 50,302 | 45 |
| 172 |
gpt-4.1-2025-04-14
|
OpenAI | 1,383 | ±4 | 50,312 | — |
| 173 |
MoonshotAI: Kimi K2 0905
|
Moonshot AI | 1,380 | ±6 | 11,589 | — |
| 176 |
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
|
1,379 | ±3 | 47,420 | — | |
| 174 |
gemini-2.5-flash-lite-preview-09-2025-no-thinking
|
1,379 | ±3 | 47,437 | — | |
| 177 |
nvidia-nemotron-3-super-120b-a12b
|
NVIDIA | 1,378 | ±7 | 7,869 | — |
| 178 |
Hunyuan TurboS (20250226)
|
Tencent | 1,377 | ±6 | 10,623 | — |
| 176 |
hunyuan-turbos-20250416
|
Tencent | 1,377 | ±6 | 10,626 | — |
| 177 |
claude-opus-4-20250514-thinking-16k
|
Anthropic | 1,377 | ±4 | 35,904 | — |
| 180 |
Z.ai: GLM 4.6V
|
Z.ai | 1,376 | ±11 | 2,831 | — |
| 181 |
DeepSeek: DeepSeek V3
|
DeepSeek | 1,375 | ±4 | 44,974 | 62 |
| 179 |
DeepSeek: DeepSeek V3 0324
|
DeepSeek | 1,375 | ±4 | 44,973 | 64 |
| 180 |
gpt-5-mini-high
|
OpenAI | 1,373 | ±5 | 26,804 | — |
| 182 |
OpenAI: GPT-5 Mini
|
OpenAI | 1,373 | ±5 | 26,799 | 66 |
| 183 |
DeepSeek: R1
|
DeepSeek | 1,373 | ±5 | 18,524 | 75 |
| 184 |
OpenAI: GPT-5.4 Nano
|
OpenAI | 1,372 | ±4 | 62,375 | — |
| 182 |
gpt-5.4-nano-high
|
OpenAI | 1,372 | ±4 | 62,396 | — |
| 185 |
Kimi K2 Preview (0711)
|
Moonshot AI | 1,371 | ±5 | 27,136 | — |
| 183 |
MoonshotAI: Kimi K2 0711
|
Moonshot AI | 1,371 | ±5 | 27,146 | — |
| 186 |
Mistral: Mistral Medium 3
|
Mistral | 1,370 | ±5 | 32,776 | — |
| 185 |
grok-3-mini-high
|
xAI | 1,370 | ±5 | 15,596 | — |
| 187 |
Grok 3 Mini (High)
|
xAI | 1,369 | ±5 | 15,591 | — |
| 186 |
gemini-2.5-flash-lite-preview-06-17-thinking
|
1,369 | ±4 | 32,381 | — | |
| 189 |
Qwen: Qwen3 Next 80B A3B Thinking
|
Alibaba | 1,368 | ±6 | 13,473 | — |
| 190 |
qwen2.5-max
|
Alibaba | 1,367 | ±4 | 32,487 | — |
| 190 |
claude-opus-4-20250514
|
Anthropic | 1,366 | ±4 | 43,043 | 68 |
| 192 |
Anthropic: Claude Opus 4
|
Anthropic | 1,366 | ±4 | 43,036 | — |
| 191 |
o1-2024-12-17
|
OpenAI | 1,366 | ±4 | 27,807 | — |
| 193 |
OpenAI: o1
|
OpenAI | 1,366 | ±4 | 27,807 | 69 |
| 194 |
OpenAI: gpt-oss-120b
|
OpenAI | 1,366 | ±4 | 30,207 | 61 |
| 195 |
grok-3-mini-beta
|
xAI | 1,364 | ±5 | 20,929 | — |
| 194 | Az amazon-nova-experimental-chat-10-09 | Amazon | 1,364 | ±11 | 2,781 | — |
| 197 | Az Amazon Nova 2 Lite | Amazon | 1,362 | ±6 | 12,410 | — |
| 195 | Az Amazon: Nova 2 Lite | Amazon | 1,362 | ±6 | 12,413 | — |
| 198 | AG ling-flash-2.0 | ant-group | 1,361 | ±7 | 6,953 | — |
| 199 |
granite-4.2-30b
|
IBM | 1,361 | ±10 | 3,407 | — |
| 200 |
MiniMax: MiniMax M2.5
|
MiniMax | 1,359 | ±4 | 42,791 | — |
| 201 |
Google: Gemma 3 27B
|
1,358 | ±4 | 46,665 | 47 | |
| 202 |
Qwen3-Coder-480B-A35B-Instruct
|
Alibaba | 1,357 | ±5 | 25,192 | — |
| 203 | I3 intellect-3 | Unknown | 1,356 | ±8 | 5,432 | — |
| 204 | In Inception: Mercury 2 | inception | 1,355 | ±10 | 3,193 | — |
| 205 |
Gemini 2.0 Flash (001)
|
1,354 | ±4 | 43,443 | — | |
| 203 | GD gemini-2.0-flash-001 | Google DeepMind,Google | 1,354 | ±4 | 43,446 | 61 |
| 204 |
o4-mini-2025-04-16
|
OpenAI | 1,353 | ±4 | 44,855 | — |
| 206 |
OpenAI: o4 Mini
|
OpenAI | 1,353 | ±4 | 44,851 | — |
| 207 |
o1-preview
|
OpenAI | 1,353 | ±5 | 31,122 | — |
| 206 |
claude-sonnet-4-20250514-thinking-32k
|
Anthropic | 1,351 | ±4 | 34,132 | — |
| 209 |
Z.ai: GLM 4.7 Flash
|
Z.ai | 1,351 | ±6 | 12,013 | — |
| 210 | St step-3 | stepfun | 1,350 | ±7 | 6,295 | — |
| 211 |
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
|
NVIDIA | 1,348 | ±5 | 15,765 | — |
| 209 |
nvidia-nemotron-3-nano-30b-a3b-bf16
|
NVIDIA | 1,348 | ±5 | 15,770 | — |
| 212 |
MiniMax: MiniMax M1
|
MiniMax | 1,343 | ±4 | 34,299 | — |
| 213 |
OpenAI: GPT-4.1 Mini
|
OpenAI | 1,341 | ±4 | 38,701 | — |
| 211 |
gpt-4.1-mini-2025-04-14
|
OpenAI | 1,340 | ±4 | 38,709 | — |
| 214 |
MiniMax: MiniMax M2
|
MiniMax | 1,340 | ±8 | 6,855 | — |
| 215 | AA Arcee AI: Trinity Large Thinking | arcee-ai | 1,340 | ±5 | 30,307 | — |
| 216 |
Qwen: Qwen3 32B
|
Alibaba | 1,340 | ±9 | 3,926 | — |
| 215 |
claude-sonnet-4-20250514
|
Anthropic | 1,339 | ±4 | 39,163 | — |
| 217 |
Anthropic: Claude Sonnet 4
|
Anthropic | 1,339 | ±4 | 39,167 | — |
| 218 | TL trinity-large-preview | Unknown | 1,339 | ±4 | 31,246 | — |
| 217 |
nvidia-llama-3.3-nemotron-super-49b-v1.5
|
NVIDIA | 1,338 | ±10 | 3,328 | — |
| 219 |
Llama 3.3 Nemotron Super 49B v1.5
|
NVIDIA | 1,338 | ±10 | 3,328 | — |
| 218 |
mistral-small-2506
|
Mistral | 1,338 | ±5 | 17,462 | — |
| 220 |
Mistral Small 3.2 (2506)
|
Mistral | 1,338 | ±5 | 17,454 | — |
| 219 |
OpenAI: o3 Mini High
|
OpenAI | 1,337 | ±5 | 18,589 | — |
| 220 | St step-1o-turbo-202506 | stepfun | 1,336 | ±7 | 8,901 | — |
| 222 | St Step-1o Turbo (202506) | stepfun | 1,336 | ±7 | 8,904 | — |
| 223 |
Google: Gemma 3 12B
|
1,334 | ±9 | 3,829 | — | |
| 224 | AG ring-flash-2.0 | ant-group | 1,334 | ±7 | 6,987 | — |
| 225 |
Z.ai: GLM 4.5V
|
Z.ai | 1,333 | ±8 | 4,821 | — |
| 227 |
Cohere: Command A
|
Cohere | 1,331 | ±3 | 55,758 | — |
| 226 |
glm-4-plus-0111
|
Z.ai | 1,331 | ±8 | 5,760 | — |
| 229 |
NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
|
NVIDIA | 1,331 | ±5 | 22,498 | — |
| 230 |
Gemini 2.0 Flash-Lite Preview (02-05)
|
1,330 | ±4 | 24,955 | — | |
| 227 |
gemini-2.0-flash-lite-preview-02-05
|
1,330 | ±4 | 24,955 | — | |
| 231 |
QwQ-32B
|
Alibaba | 1,329 | ±4 | 25,174 | 69 |
| 229 |
nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4
|
NVIDIA | 1,329 | ±6 | 19,938 | — |
| 232 |
Qwen: Qwen-Plus
|
Alibaba | 1,326 | ±8 | 5,819 | — |
| 230 |
qwen-plus-0125
|
Alibaba | 1,326 | ±8 | 5,819 | — |
| 233 | St Step-2 16K Exp (202412) | stepfun | 1,321 | ±9 | 4,833 | — |
| 231 | St step-2-16k-exp-202412 | stepfun | 1,321 | ±9 | 4,833 | — |
| 234 |
OpenAI: GPT-5 Nano
|
OpenAI | 1,320 | ±7 | 8,134 | 67 |
| 232 |
gpt-5-nano-high
|
OpenAI | 1,320 | ±7 | 8,132 | — |
| 233 |
hunyuan-turbos-20250226
|
Tencent | 1,320 | ±12 | 2,220 | — |
| 236 |
llama-3.1-nemotron-ultra-253b-v1
|
NVIDIA | 1,320 | ±12 | 2,549 | — |
| 237 |
OpenAI: o3 Mini
|
OpenAI | 1,319 | ±4 | 56,742 | 86 |
| 238 |
IBM: Granite 4.2 8B
|
IBM | 1,319 | ±11 | 3,259 | — |
| 237 |
gemini-1.5-pro-002
|
1,319 | ±3 | 55,606 | — | |
| 240 |
o1-mini
|
OpenAI | 1,317 | ±4 | 51,981 | 64 |
| 241 |
Qwen: Qwen3 30B A3B
|
Alibaba | 1,317 | ±5 | 26,155 | — |
| 240 |
claude-3-7-sonnet-20250219-thinking-32k
|
Anthropic | 1,314 | ±4 | 38,159 | — |
| 243 |
Hunyuan Turbo (0110)
|
Tencent | 1,311 | ±11 | 2,290 | — |
| 241 |
hunyuan-turbo-0110
|
Tencent | 1,311 | ±11 | 2,290 | — |
| 244 | A2 olmo-3.1-32b-instruct | Allen Institute for AI | 1,311 | ±6 | 11,805 | — |
| 245 |
Llama 3.3 Nemotron Super 49B v1
|
NVIDIA | 1,308 | ±12 | 2,218 | — |
| 243 |
llama-3.3-nemotron-49b-super-v1
|
NVIDIA | 1,308 | ±12 | 2,218 | — |
| 246 |
Google: Gemma 3n 4B
|
1,306 | ±5 | 22,142 | — | |
| 247 |
Grok 2 (2024-08-13)
|
xAI | 1,305 | ±4 | 63,498 | — |
| 245 |
grok-2-2024-08-13
|
xAI | 1,305 | ±4 | 63,498 | — |
| 248 | YL yi-lightning | Unknown | 1,302 | ±5 | 27,332 | — |
| 249 |
OpenAI: GPT-4o
|
OpenAI | 1,300 | ±3 | 112,881 | 27 |
| 247 |
OpenAI: GPT-4o (2024-05-13)
|
OpenAI | 1,300 | ±3 | 112,881 | — |
| 250 | A2 AllenAI: Olmo 3 32B Think | Allen Institute for AI | 1,300 | ±8 | 5,825 | — |
| 249 |
claude-3-7-sonnet-20250219
|
Anthropic | 1,299 | ±4 | 42,572 | 74 |
| 251 |
Claude 3.7 Sonnet (Thinking)
|
Anthropic | 1,299 | ±4 | 42,572 | — |
| 252 |
Qwen2.5-Plus (1127)
|
Alibaba | 1,299 | ±6 | 10,187 | — |
| 250 |
qwen2.5-plus-1127
|
Alibaba | 1,299 | ±6 | 10,187 | — |
| 253 |
Claude 3.5 Sonnet (October 2024)
|
Anthropic | 1,298 | ±3 | 87,771 | — |
| 251 |
claude-3-5-sonnet-20241022
|
Anthropic | 1,298 | ±3 | 87,769 | 45 |
| 252 |
deepseek-v2.5-1210
|
DeepSeek | 1,294 | ±8 | 6,795 | — |
| 255 |
granite-4.2-3b
|
IBM | 1,294 | ±11 | 3,260 | — |
| 256 | AV athene-v2-chat | Unknown | 1,291 | ±5 | 24,739 | — |
| 257 |
Google: Gemma 3 4B
|
1,291 | ±9 | 4,171 | — | |
| 258 |
IBM: Granite 4.1 8B
|
IBM | 1,291 | ±10 | 4,177 | — |
| 259 |
glm-4-plus
|
Z.ai | 1,290 | ±5 | 26,126 | — |
| 260 | A2 molmo-2-8b | Allen Institute for AI | 1,288 | ±21 | 823 | — |
| 261 |
Hunyuan Large (2025-02-10)
|
Tencent | 1,288 | ±10 | 3,738 | — |
| 259 |
hunyuan-large-2025-02-10
|
Tencent | 1,288 | ±10 | 3,738 | — |
| 262 |
OpenAI: gpt-oss-20b
|
OpenAI | 1,287 | ±6 | 10,417 | 41 |
| 263 |
llama-4-maverick-17b-128e-instruct
|
Meta | 1,287 | ±4 | 39,444 | — |
| 262 |
gemini-1.5-flash-002
|
1,287 | ±4 | 34,902 | — | |
| 265 |
OpenAI: GPT-4o-mini
|
OpenAI | 1,286 | ±4 | 68,705 | 31 |
| 263 |
OpenAI: GPT-4o-mini (2024-07-18)
|
OpenAI | 1,286 | ±4 | 68,705 | — |
| 264 |
gpt-4.1-nano-2025-04-14
|
OpenAI | 1,285 | ±8 | 6,103 | — |
| 266 |
OpenAI: GPT-4.1 Nano
|
OpenAI | 1,285 | ±8 | 6,103 | — |
| 265 |
llama-3.1-405b-instruct-bf16
|
Meta | 1,284 | ±4 | 41,375 | — |
| 268 |
llama-3.1-nemotron-70b-instruct
|
NVIDIA | 1,283 | ±8 | 7,140 | — |
| 267 |
OpenAI: GPT-4o (2024-08-06)
|
OpenAI | 1,282 | ±4 | 45,499 | — |
| 270 | IA mercury | inception-ai | 1,282 | ±14 | 1,964 | — |
| 271 |
qwen-max
|
Alibaba | 1,282 | ±6 | 16,478 | — |
| 268 |
qwen-max-0919
|
Alibaba | 1,282 | ±6 | 16,478 | — |
| 272 |
Llama-3.1-405B-Instruct
|
Meta | 1,282 | ±4 | 59,656 | — |
| 270 |
llama-3.1-405b-instruct-fp8
|
Meta | 1,282 | ±4 | 59,656 | — |
| 271 |
claude-3-5-sonnet-20240620
|
Anthropic | 1,281 | ±3 | 82,419 | — |
| 274 |
Grok 2 mini (2024-08-13)
|
xAI | 1,281 | ±4 | 52,567 | — |
| 272 |
grok-2-mini-2024-08-13
|
xAI | 1,281 | ±4 | 52,567 | — |
| 275 |
Llama-4-Scout-17B-16E-Instruct
|
Meta | 1,279 | ±5 | 29,830 | — |
| 276 |
Gemini Advanced (0514)
|
1,279 | ±5 | 50,148 | — | |
| 274 |
gemini-advanced-0514
|
1,279 | ±5 | 50,148 | — | |
| 277 |
Mistral Small 3.1 24B Instruct (2503)
|
Mistral | 1,277 | ±5 | 32,721 | — |
| 275 |
mistral-small-3.1-24b-instruct-2503
|
Mistral | 1,277 | ±5 | 32,727 | — |
| 278 |
Meta: Llama 3.3 70B Instruct
|
Meta | 1,274 | ±3 | 54,493 | 34 |
| 279 |
Hunyuan Standard (2025-02-10)
|
Tencent | 1,274 | ±10 | 3,904 | — |
| 277 |
hunyuan-standard-2025-02-10
|
Tencent | 1,274 | ±10 | 3,904 | — |
| 280 |
Gemini 1.5 Pro (001)
|
1,273 | ±4 | 79,138 | — | |
| 278 |
gemini-1.5-pro-001
|
1,273 | ±4 | 79,138 | — | |
| 281 |
OpenAI: GPT-4 Turbo
|
OpenAI | 1,272 | ±4 | 98,114 | — |
| 279 |
gpt-4-turbo-2024-04-09
|
OpenAI | 1,272 | ±4 | 98,114 | — |
| 282 | A2 olmo-3.1-32b-think | Allen Institute for AI | 1,271 | ±7 | 8,299 | — |
| 283 |
deepseek-v2.5
|
DeepSeek | 1,271 | ±5 | 24,572 | — |
| 284 |
Qwen2.5 72B Instruct
|
Alibaba | 1,269 | ±4 | 39,406 | — |
| 285 |
Mistral Large 2 (2407)
|
Mistral | 1,266 | ±4 | 45,459 | — |
| 283 |
Mistral Large 2407
|
Mistral | 1,266 | ±4 | 45,459 | — |
| 284 |
mistral-large-2411
|
Mistral | 1,265 | ±4 | 28,073 | 37 |
| 287 | A7 Athene 70B (0725) | Unknown | 1,265 | ±6 | 19,621 | — |
| 285 | A7 athene-70b-0725 | Unknown | 1,265 | ±6 | 19,621 | — |
| 288 |
OpenAI: GPT-4 Turbo Preview
|
OpenAI | 1,263 | ±4 | 100,105 | — |
| 286 |
gpt-4-1106-preview
|
OpenAI | 1,263 | ±4 | 100,105 | — |
| 289 |
hunyuan-large-vision
|
Tencent | 1,263 | ±9 | 5,283 | — |
| 288 |
gpt-4-0125-preview
|
OpenAI | 1,262 | ±4 | 93,439 | — |
| 291 |
Claude 3 Opus (20240229)
|
Anthropic | 1,262 | ±3 | 194,909 | — |
| 289 |
claude-3-opus-20240229
|
Anthropic | 1,262 | ±3 | 194,909 | 32 |
| 292 |
Meta: Llama 3.1 70B Instruct
|
Meta | 1,261 | ±4 | 55,240 | — |
| 293 | Az Amazon Nova Pro 1.0 | Amazon | 1,259 | ±5 | 24,745 | — |
| 291 | Az amazon.nova-pro-v1:0 | Amazon | 1,259 | ±5 | 24,745 | — |
| 294 | A2 llama-3.1-tulu-3-70b | Allen Institute for AI | 1,256 | ±10 | 2,846 | — |
| 295 |
Claude 3.5 Haiku (20241022)
|
Anthropic | 1,255 | ±3 | 69,055 | — |
| 293 |
claude-3-5-haiku-20241022
|
Anthropic | 1,255 | ±3 | 69,061 | 30 |
| 294 |
magistral-medium-2506
|
Mistral | 1,255 | ±6 | 11,510 | — |
| 296 |
Magistral Medium (2506)
|
Mistral | 1,255 | ±6 | 11,509 | — |
| 297 | Re Reka Core (20240904) | Reka AI | 1,248 | ±7 | 7,312 | — |
| 295 | Re reka-core-20240904 | Reka AI | 1,248 | ±7 | 7,312 | — |
| 298 |
Granite-4.0-H-Small
|
IBM | 1,242 | ±8 | 5,628 | — |
| 296 |
ibm-granite-h-small
|
IBM | 1,241 | ±8 | 5,630 | — |
| 299 |
Gemini 1.5 Flash (001)
|
1,239 | ±4 | 62,833 | — | |
| 297 |
gemini-1.5-flash-001
|
1,239 | ±4 | 62,833 | — | |
| 300 | J1 jamba-1.5-large | Unknown | 1,237 | ±7 | 8,662 | — |
| 301 |
Mistral Small 24B Instruct (2501)
|
Mistral | 1,234 | ±6 | 14,681 | — |
| 299 |
Mistral: Mistral Small 3
|
Mistral | 1,234 | ±6 | 14,681 | — |
| 302 |
Google: Gemma 2 27B
|
1,231 | ±3 | 75,754 | 21 | |
| 303 |
Qwen2.5 Coder 32B Instruct
|
Alibaba | 1,230 | ±8 | 5,432 | — |
| 302 |
Cohere: Command R+ (08-2024)
|
Cohere | 1,229 | ±7 | 9,866 | — |
| 305 | Az Amazon Nova Lite 1.0 | Amazon | 1,228 | ±5 | 19,372 | — |
| 303 | Az amazon.nova-lite-v1:0 | Amazon | 1,228 | ±5 | 19,372 | — |
| 306 |
llama-3.1-nemotron-51b-instruct
|
NVIDIA | 1,228 | ±10 | 3,749 | — |
| 307 |
gemma-2-9b-it-simpo
|
1,227 | ±7 | 10,072 | — | |
| 308 |
GLM-4 (0520)
|
Z.ai | 1,226 | ±7 | 9,788 | — |
| 306 |
glm-4-0520
|
Z.ai | 1,226 | ±7 | 9,788 | — |
| 309 |
Gemini 1.5 Flash-8B (001)
|
1,226 | ±4 | 35,558 | — | |
| 307 |
gemini-1.5-flash-8b-001
|
1,226 | ±4 | 35,558 | — | |
| 310 |
nemotron-4-340b-instruct
|
NVIDIA | 1,225 | ±5 | 19,659 | — |
| 311 |
Aya Expanse 32B
|
Cohere | 1,224 | ±5 | 27,124 | — |
| 309 |
c4ai-aya-expanse-32b
|
Cohere | 1,224 | ±5 | 27,124 | — |
| 312 |
llama-3-70b-instruct
|
Meta | 1,221 | ±4 | 156,876 | — |
| 313 |
Claude 3 Sonnet (20240229)
|
Anthropic | 1,218 | ±4 | 109,284 | — |
| 311 |
claude-3-sonnet-20240229
|
Anthropic | 1,218 | ±4 | 109,284 | — |
| 314 | A2 OLMo 2 32B Instruct (0325) | Allen Institute for AI | 1,218 | ±11 | 3,334 | — |
| 312 | A2 olmo-2-0325-32b-instruct | Allen Institute for AI | 1,218 | ±11 | 3,334 | — |
| 315 | Re Reka Flash (20240904) | Reka AI | 1,218 | ±7 | 7,536 | — |
| 313 | Re reka-flash-20240904 | Reka AI | 1,218 | ±7 | 7,536 | — |
| 316 |
Microsoft: Phi 4
|
Microsoft | 1,217 | ±5 | 24,126 | 41 |
| 317 | Az Amazon Nova Micro 1.0 | Amazon | 1,208 | ±5 | 19,364 | — |
| 315 | Az amazon.nova-micro-v1:0 | Amazon | 1,208 | ±5 | 19,364 | — |
| 318 |
gemma-2-9b-it
|
1,207 | ±4 | 54,611 | 13 | |
| 317 |
gpt-4-0314
|
OpenAI | 1,206 | ±5 | 54,173 | — |
| 320 |
Cohere: Command R (08-2024)
|
Cohere | 1,204 | ±4 | 77,554 | — |
| 318 |
command-r-plus
|
Cohere | 1,204 | ±4 | 77,554 | — |
| 321 |
qwen2-72b-instruct
|
Alibaba | 1,203 | ±5 | 37,325 | — |
| 322 |
hunyuan-standard-256k
|
Tencent | 1,202 | ±12 | 2,728 | — |
| 323 |
Anthropic: Claude 3 Haiku
|
Anthropic | 1,195 | ±4 | 117,701 | — |
| 324 | A2 llama-3.1-tulu-3-8b | Allen Institute for AI | 1,193 | ±10 | 2,896 | — |
| 325 |
deepseek-coder-v2
|
DeepSeek | 1,191 | ±6 | 15,147 | — |
| 326 |
Mistral: Ministral 8B
|
Mistral | 1,191 | ±9 | 4,781 | — |
| 324 |
ministral-8b-2410
|
Mistral | 1,191 | ±9 | 4,781 | — |
| 328 | J1 jamba-1.5-mini | Unknown | 1,187 | ±7 | 8,858 | — |
| 329 |
Meta: Llama 3.1 8B Instruct
|
Meta | 1,187 | ±4 | 49,605 | — |
| 330 |
OpenAI: GPT-4
|
OpenAI | 1,186 | ±4 | 88,723 | — |
| 328 |
gpt-4-0613
|
OpenAI | 1,186 | ±4 | 88,723 | — |
| 331 |
Aya Expanse 8B
|
Cohere | 1,185 | ±7 | 9,818 | — |
| 329 |
c4ai-aya-expanse-8b
|
Cohere | 1,185 | ±7 | 9,818 | — |
| 332 |
Mistral Large
|
Mistral | 1,176 | ±5 | 62,436 | — |
| 330 |
mistral-large-2402
|
Mistral | 1,176 | ±5 | 62,436 | — |
| 333 |
qwen1.5-110b-chat
|
Alibaba | 1,175 | ±6 | 26,195 | — |
| 334 | 0A Yi-1.5-34B-Chat | 01.AI | 1,173 | ±5 | 24,146 | — |
| 333 | Re reka-flash-21b-20240226-online | Reka AI | 1,170 | ±7 | 15,450 | — |
| 336 |
qwen1.5-72b-chat
|
Alibaba | 1,166 | ±5 | 39,302 | — |
| 337 |
llama-3-8b-instruct
|
Meta | 1,166 | ±4 | 104,642 | — |
| 338 |
mistral-medium
|
Mistral | 1,165 | ±5 | 34,550 | — |
| 339 | Re Reka Flash 21B (20240226) | Reka AI | 1,165 | ±6 | 24,806 | — |
| 337 | Re reka-flash-21b-20240226 | Reka AI | 1,165 | ±6 | 24,806 | — |
| 341 |
mixtral-8x22b-instruct-v0.1
|
Mistral | 1,162 | ±5 | 51,416 | — |
| 342 |
QwQ-32B-Preview
|
Alibaba | 1,162 | ±11 | 3,231 | — |
| 343 | I5 internlm2_5-20b-chat | Unknown | 1,158 | ±7 | 9,901 | — |
| 344 |
gemma-2-2b-it
|
1,156 | ±4 | 46,616 | — | |
| 345 |
granite-3.1-8b-instruct
|
IBM | 1,150 | ±11 | 3,090 | — |
| 346 |
gemini-pro
|
1,149 | ±7 | 18,354 | — | |
| 344 |
gemini-pro-dev-api
|
1,149 | ±7 | 18,354 | — | |
| 347 | ZO zephyr-orpo-141b-A35b-v0.1 | Unknown | 1,144 | ±11 | 4,652 | — |
| 348 |
phi-3-medium-4k-instruct
|
Microsoft | 1,138 | ±5 | 25,055 | — |
| 349 |
qwen1.5-32b-chat
|
Alibaba | 1,137 | ±6 | 21,741 | — |
| 350 | SL starling-lm-7b-beta | Unknown | 1,132 | ±7 | 16,056 | — |
| 351 |
Mixtral-8x7B-Instruct-v0.1
|
Mistral | 1,132 | ±4 | 73,503 | — |
| 353 | 0A Yi-34B-Chat | 01.AI | 1,128 | ±7 | 15,483 | — |
| 354 |
qwen1.5-14b-chat
|
Alibaba | 1,128 | ±7 | 17,839 | — |
| 355 |
granite-3.1-2b-instruct
|
IBM | 1,127 | ±11 | 3,188 | — |
| 356 |
OpenAI: GPT-3.5 Turbo
|
OpenAI | 1,125 | ±5 | 66,207 | — |
| 354 |
gpt-3.5-turbo-0125
|
OpenAI | 1,125 | ±5 | 66,207 | — |
| 357 | T2 tulu-2-dpo-70b | Unknown | 1,121 | ±10 | 6,535 | — |
| 358 |
wizardlm-70b
|
Microsoft | 1,119 | ±9 | 8,214 | — |
| 359 | DI dbrx-instruct-preview | Unknown | 1,119 | ±6 | 32,191 | — |
| 360 |
llama-2-70b-chat
|
Meta | 1,115 | ±5 | 38,492 | — |
| 361 |
nous-hermes-2-mixtral-8x7b-dpo
|
Nous Research | 1,112 | ±12 | 3,777 | — |
| 362 |
Phi-3-small-8k-instruct
|
Microsoft | 1,110 | ±6 | 17,766 | — |
| 363 |
Meta: Llama 3.2 3B Instruct
|
Meta | 1,110 | ±8 | 7,936 | — |
| 364 | SL starling-lm-7b-alpha | Unknown | 1,108 | ±8 | 10,224 | — |
| 365 | O3 openchat-3.5 | Unknown | 1,107 | ±8 | 12,637 | — |
| 363 | O3 openchat-3.5-0106 | Unknown | 1,107 | ±8 | 12,637 | — |
| 366 | V3 vicuna-33b | Unknown | 1,105 | ±6 | 22,479 | — |
| 367 |
deepseek-llm-67b-chat
|
DeepSeek | 1,105 | ±12 | 4,932 | — |
| 368 |
snowflake-arctic-instruct
|
Snowflake | 1,101 | ±6 | 32,832 | — |
| 369 |
Llama 2 70B SteerLM Chat
|
NVIDIA | 1,098 | ±12 | 3,585 | — |
| 367 |
llama2-70b-steerlm-chat
|
NVIDIA | 1,098 | ±12 | 3,585 | — |
| 371 |
granite-3.0-8b-instruct
|
IBM | 1,096 | ±9 | 6,638 | — |
| 370 |
gpt-3.5-turbo-1106
|
OpenAI | 1,094 | ±9 | 16,619 | — |
| 373 |
gemma-1.1-7b-it
|
1,094 | ±6 | 23,893 | — | |
| 374 | O2 openhermes-2.5-mistral-7b | Unknown | 1,092 | ±10 | 5,006 | — |
| 375 |
mistral-7b-instruct-v0.2
|
Mistral | 1,090 | ±7 | 19,402 | — |
| 376 |
llama-2-13b-chat
|
Meta | 1,084 | ±7 | 19,174 | — |
| 377 |
qwen1.5-7b-chat
|
Alibaba | 1,083 | ±10 | 4,737 | — |
| 378 |
solar-10.7b-instruct-v1.0
|
Upstage | 1,083 | ±13 | 4,155 | — |
| 379 | D2 dolphin-2.2.1-mistral-7b | Unknown | 1,081 | ±15 | 1,679 | — |
| 378 |
phi-3-mini-4k-instruct-june-2024
|
Microsoft | 1,080 | ±6 | 12,297 | — |
| 381 |
granite-3.0-2b-instruct
|
IBM | 1,080 | ±8 | 6,837 | — |
| 382 |
wizardlm-13b
|
Microsoft | 1,077 | ±9 | 7,044 | — |
| 383 |
Phi-3-mini-4k-instruct
|
Microsoft | 1,073 | ±6 | 20,118 | — |
| 384 | Z7 zephyr-7b-beta | Unknown | 1,069 | ±9 | 11,118 | — |
| 385 | M3 mpt-30b-chat | Unknown | 1,069 | ±12 | 2,572 | — |
| 386 |
Code Llama 34B Instruct
|
Meta | 1,065 | ±9 | 7,366 | — |
| 384 |
codellama-34b-instruct
|
Meta | 1,065 | ±9 | 7,366 | — |
| 387 | Z7 zephyr-7b-alpha | Unknown | 1,058 | ±16 | 1,785 | — |
| 388 | V1 vicuna-13b | Unknown | 1,058 | ±7 | 19,367 | — |
| 389 |
Code Llama 70B Instruct
|
Meta | 1,057 | ±18 | 1,143 | — |
| 387 |
codellama-70b-instruct
|
Meta | 1,057 | ±18 | 1,143 | — |
| 390 |
gemma-7b-it
|
1,056 | ±10 | 8,925 | — | |
| 391 |
Meta: Llama 3.2 1B Instruct
|
Meta | 1,055 | ±8 | 8,045 | — |
| 392 | F1 falcon-180b-chat | Unknown | 1,054 | ±17 | 1,295 | — |
| 393 |
llama-2-7b-chat
|
Meta | 1,053 | ±7 | 14,148 | — |
| 394 | G3 guanaco-33b | Unknown | 1,053 | ±12 | 2,921 | — |
| 395 |
qwen-14b-chat
|
Alibaba | 1,051 | ±11 | 4,964 | — |
| 396 |
phi-3-mini-128k-instruct
|
Microsoft | 1,050 | ±7 | 20,685 | — |
| 397 | S1 smollm2-1.7b-instruct | Unknown | 1,042 | ±14 | 2,199 | — |
| 398 | SN stripedhyena-nous-7b | Unknown | 1,038 | ±11 | 5,182 | — |
| 399 | A2 olmo-7b-instruct | Allen Institute for AI | 1,032 | ±11 | 6,328 | — |
| 400 | V7 vicuna-7b | Unknown | 1,031 | ±9 | 6,923 | — |
| 401 |
palm-2
|
1,027 | ±9 | 8,554 | — | |
| 402 |
mistral-7b-instruct
|
Mistral | 1,023 | ±9 | 8,977 | — |
| 403 |
gemma-1.1-2b-it
|
1,022 | ±8 | 10,854 | — | |
| 404 |
gemma-2b-it
|
1,002 | ±11 | 4,780 | — | |
| 405 |
qwen1.5-4b-chat
|
Alibaba | 997 | ±9 | 7,597 | — |
| 406 | K1 koala-13b | Unknown | 990 | ±10 | 6,965 | — |
| 407 | C6 chatglm3-6b | Unknown | 972 | ±12 | 4,658 | — |
| 408 | G1 gpt4all-13b-snoozy | Unknown | 956 | ±15 | 1,743 | — |
| 409 | M7 mpt-7b-chat | Unknown | 955 | ±12 | 3,924 | — |
| 410 | R4 RWKV-4-Raven-14B | Unknown | 948 | ±11 | 4,845 | — |
| 411 | C6 chatglm2-6b | Unknown | 939 | ±13 | 2,658 | — |
| 412 | A1 alpaca-13b | Unknown | 933 | ±11 | 5,745 | — |
| 413 |
chatglm-6b
|
Z.ai | 918 | ±12 | 4,914 | — |
| 414 | OP OpenAssistant Pythia 12B | Unknown | 916 | ±11 | 6,310 | — |
| 412 | OP oasst-pythia-12b | Unknown | 916 | ±11 | 6,310 | — |
| 415 | FT fastchat-t5-3b | Unknown | 894 | ±12 | 4,203 | — |
| 416 | ST stablelm-tuned-alpha-7b | Unknown | 867 | ±13 | 3,287 | — |
| 417 | D2 Dolly 2.0 12B | Unknown | 851 | ±13 | 3,412 | — |
| 415 | DV dolly-v2-12b | Unknown | 851 | ±13 | 3,412 | — |
| 418 |
llama-13b
|
Meta | 833 | ±16 | 2,391 | — |
The Known Good
Text Arena (style controlled) — full ranking
551 models rated
17,764,214 votes countedRatings captured 25 Oct 2026 Source: Arena
| # | Model | Creator | Elo | 95% CI | Votes | Known Good Index |
|---|---|---|---|---|---|---|
| 1 |
gemini-4-argon-high
|
1,525 | ±9 | 4,903 | — | |
| 1 |
Google: Gemini 4 Argon
|
1,517 | ±7 | 10,083 | — | |
| 2 |
muse-wonder-max
|
Meta | 1,513 | ±13 | 1,944 | — |
| 2 |
Anthropic: Claude Opus 5.5
|
Anthropic | 1,509 | ±7 | 10,322 | — |
| 3 |
Meta: Muse Wonder
|
Meta | 1,509 | ±8 | 6,001 | — |
| 3 |
claude-opus-5.5-high
|
Anthropic | 1,508 | ±8 | 7,687 | — |
| 2 |
claude-opus-4-6-thinking
|
Anthropic | 1,505 | ±4 | 72,425 | — |
| 4 |
claude-fable-5-high
|
Anthropic | 1,503 | ±4 | 41,439 | — |
| 4 |
Anthropic: Claude Fable 5
|
Anthropic | 1,503 | ±4 | 44,253 | — |
| 5 |
Anthropic: Claude Fable 5.1
|
Anthropic | 1,503 | ±6 | 16,343 | — |
| 5 |
claude-opus-4-6-high
|
Anthropic | 1,503 | ±3 | 80,827 | — |
| 3 |
claude-opus-4-7-thinking
|
Anthropic | 1,502 | ±4 | 60,222 | — |
| 6 |
claude-opus-4-7-high
|
Anthropic | 1,501 | ±4 | 65,125 | — |
| 7 |
claude-fable-5.1-max
|
Anthropic | 1,501 | ±6 | 14,121 | — |
| 8 |
Anthropic: Claude Opus 4.6
|
Anthropic | 1,497 | ±3 | 88,206 | 86 |
| 9 |
gemini-3.8-flash-high
|
1,496 | ±5 | 35,670 | — | |
| 9 |
Google: Gemini 3.8 Flash
|
1,496 | ±4 | 43,997 | — | |
| 10 |
Meta: Muse Spark 1.3
|
Meta | 1,496 | ±5 | 20,506 | — |
| 11 |
muse-spark-1.3-max
|
Meta | 1,494 | ±6 | 16,731 | — |
| 11 |
Anthropic: Claude Opus 4.7
|
Anthropic | 1,494 | ±4 | 66,183 | 90 |
| 12 |
Meta: Muse Spark 1.2
|
Meta | 1,491 | ±7 | 10,470 | — |
| 14 |
Anthropic: Claude Opus 5
|
Anthropic | 1,491 | ±4 | 71,020 | — |
| 14 |
claude-opus-5-high
|
Anthropic | 1,490 | ±4 | 65,663 | — |
| 15 |
Meta: Muse Spark 1.1
|
Meta | 1,490 | ±4 | 46,121 | — |
| 16 |
Google: Gemini 3.7 Flash
|
1,490 | ±5 | 30,501 | — | |
| 15 |
claude-opus-5-max
|
Anthropic | 1,490 | ±5 | 31,907 | — |
| 17 |
muse-spark
|
Meta | 1,489 | ±6 | 14,147 | — |
| 17 |
kimi-k3-max
|
Moonshot AI | 1,488 | ±5 | 32,036 | — |
| 18 |
MoonshotAI: Kimi K3
|
Moonshot AI | 1,487 | ±4 | 35,379 | — |
| 18 |
gemini-3.7-flash-high
|
1,487 | ±5 | 26,328 | — | |
| 19 |
Google: Gemini 3.1 Pro Preview
|
1,487 | ±3 | 130,819 | 93 | |
| 20 |
Gemini 3 Pro
|
1,486 | ±4 | 42,054 | — | |
| 21 |
OpenAI: GPT-5.6 Sol
|
OpenAI | 1,485 | ±4 | 42,713 | — |
| 21 |
gpt-5.6-sol-xhigh
|
OpenAI | 1,485 | ±4 | 40,442 | — |
| 22 |
gpt-6.1-sol-max
|
OpenAI | 1,484 | ±8 | 6,320 | — |
| 22 |
Google: Gemini 3.6 Flash
|
1,483 | ±4 | 36,102 | — | |
| 23 |
Qwen: Qwen3.8 Max
|
Alibaba | 1,483 | ±5 | 30,500 | — |
| 23 |
gemini-3.6-flash-high
|
1,483 | ±4 | 36,122 | — | |
| 25 |
claude-opus-4-8-high
|
Anthropic | 1,482 | ±4 | 64,100 | — |
| 26 |
gpt-5.5-high
|
OpenAI | 1,481 | ±4 | 69,401 | — |
| 17 |
claude-opus-4-8-thinking
|
Anthropic | 1,481 | ±5 | 40,409 | — |
| 26 |
Z.ai: GLM 5.3
|
Z.ai | 1,481 | ±5 | 25,144 | — |
| 27 |
OpenAI: GPT-6.1 Sol
|
OpenAI | 1,480 | ±7 | 8,305 | — |
| 28 | Mi Xiaomi: MiMo-V2.6-Pro | Xiaomi | 1,480 | ±9 | 4,067 | — |
| 28 |
glm-5.3-max
|
Z.ai | 1,479 | ±5 | 22,543 | — |
| 29 |
Anthropic: Claude Sonnet 5.5
|
Anthropic | 1,478 | ±7 | 8,977 | — |
| 29 |
gemini-3.5-flash-high
|
1,477 | ±4 | 48,486 | — | |
| 30 |
Google: Gemini 3.5 Flash
|
1,477 | ±4 | 48,504 | 95 | |
| 30 |
gpt-6-astra-max
|
OpenAI | 1,477 | ±6 | 12,163 | — |
| 31 |
OpenAI: GPT-5.5
|
OpenAI | 1,477 | ±4 | 70,998 | 93 |
| 32 |
OpenAI: GPT-6 Astra
|
OpenAI | 1,476 | ±6 | 14,076 | — |
| 34 |
DeepSeek-V4.1-Flash-20260910 (Max)
|
DeepSeek | 1,476 | ±6 | 13,750 | — |
| 35 |
Z.ai: GLM 5.3 Flash
|
Z.ai | 1,476 | ±5 | 38,359 | — |
| 32 |
glm-5.2-max
|
Z.ai | 1,476 | ±4 | 49,820 | — |
| 33 |
gemini-3.5-flash-medium
|
1,476 | ±4 | 47,292 | — | |
| 34 |
gpt-5.2-chat-latest-20260210
|
OpenAI | 1,476 | ±4 | 35,999 | — |
| 36 |
OpenAI: GPT-5.2 Chat
|
OpenAI | 1,476 | ±4 | 35,982 | — |
| 37 |
Z.ai: GLM 5.2
|
Z.ai | 1,475 | ±4 | 52,283 | 91 |
| 35 |
gpt-5.4-high
|
OpenAI | 1,475 | ±4 | 64,776 | — |
| 36 |
claude-sonnet-5.5-xhigh
|
Anthropic | 1,475 | ±8 | 6,831 | — |
| 37 |
grok-4.20-beta1
|
xAI | 1,475 | ±5 | 27,908 | — |
| 39 |
Grok 4.20 Beta 1
|
xAI | 1,475 | ±5 | 27,914 | — |
| 38 |
deepseek-v4.1-flash-max
|
DeepSeek | 1,475 | ±6 | 12,793 | — |
| 40 |
Anthropic: Claude Opus 4.8
|
Anthropic | 1,474 | ±4 | 65,208 | — |
| 41 |
qwen3.7-max-preview
|
Alibaba | 1,474 | ±10 | 3,941 | — |
| 42 |
claude-opus-4-5-20251101-high-32k
|
Anthropic | 1,474 | ±4 | 37,509 | — |
| 43 |
gpt-5.5-instant
|
OpenAI | 1,473 | ±5 | 27,163 | — |
| 29 |
claude-opus-4-5-20251101-thinking-32k
|
Anthropic | 1,473 | ±4 | 37,213 | — |
| 45 |
Anthropic: Claude Sonnet 4.6
|
Anthropic | 1,472 | ±4 | 70,953 | 80 |
| 46 |
Grok 4.20 Beta (Reasoning, 0309)
|
xAI | 1,472 | ±4 | 66,418 | — |
| 46 |
grok-4.20-beta-0309-reasoning
|
xAI | 1,472 | ±4 | 66,436 | — |
| 47 |
Grok 4.20 Multi-Agent Beta (0309)
|
xAI | 1,471 | ±4 | 64,928 | — |
| 47 |
grok-4.20-multi-agent-beta-0309
|
xAI | 1,470 | ±4 | 64,946 | — |
| 48 |
Anthropic: Claude Opus 4.5
|
Anthropic | 1,470 | ±3 | 72,850 | 71 |
| 49 |
OpenAI: GPT-5.6 Terra
|
OpenAI | 1,467 | ±4 | 46,470 | — |
| 50 |
ernie-5.1
|
Baidu | 1,467 | ±5 | 39,474 | — |
| 51 | Mi Xiaomi: MiMo-V2.5-Pro | Xiaomi | 1,466 | ±4 | 77,883 | — |
| 51 |
gpt-5.6-terra-xhigh
|
OpenAI | 1,466 | ±4 | 43,271 | — |
| 52 |
SpaceXAI: Grok 4.5
|
xAI | 1,466 | ±4 | 39,880 | — |
| 53 |
Z.ai: GLM 5.1
|
Z.ai | 1,465 | ±4 | 65,402 | 89 |
| 53 |
grok-4.1-thinking
|
xAI | 1,465 | ±3 | 66,509 | — |
| 55 |
OpenAI: GPT-5.4
|
OpenAI | 1,465 | ±4 | 67,855 | 88 |
| 56 |
deepseek-v4-pro-high-20260813
|
DeepSeek | 1,465 | ±7 | 9,800 | — |
| 56 |
qwen3.5-max-preview
|
Alibaba | 1,465 | ±5 | 22,601 | — |
| 58 |
Anthropic: Claude Sonnet 5
|
Anthropic | 1,461 | ±4 | 51,784 | — |
| 58 |
claude-sonnet-5-high
|
Anthropic | 1,461 | ±4 | 49,595 | — |
| 59 |
MoonshotAI: Kimi K2.6
|
Moonshot AI | 1,461 | ±4 | 40,026 | 92 |
| 60 |
Qwen: Qwen3.6 Max Preview
|
Alibaba | 1,461 | ±8 | 5,423 | 89 |
| 61 |
grok-4.1
|
xAI | 1,459 | ±3 | 68,621 | — |
| 62 |
OpenAI: GPT-6 Sol
|
OpenAI | 1,459 | ±6 | 14,707 | — |
| 61 |
gpt-6-sol-max
|
OpenAI | 1,459 | ±6 | 12,466 | — |
| 63 |
gemini-3-flash
|
1,458 | ±3 | 90,998 | — | |
| 64 |
DeepSeek: DeepSeek V4 Pro 0423
|
DeepSeek | 1,458 | ±4 | 57,588 | 93 |
| 65 |
Z.ai: GLM 5
|
Z.ai | 1,457 | ±4 | 29,267 | 77 |
| 66 |
claude-sonnet-4-5-20250929-high-32k
|
Anthropic | 1,456 | ±3 | 83,940 | — |
| 66 |
SpaceXAI: Grok 4.6
|
xAI | 1,456 | ±5 | 32,189 | — |
| 67 |
Anthropic: Claude Sonnet 4.5
|
Anthropic | 1,456 | ±3 | 83,906 | — |
| 68 |
dola-seed-2.0-pro
|
ByteDance | 1,456 | ±3 | 79,130 | — |
| 54 |
claude-sonnet-4-5-20250929-thinking-32k
|
Anthropic | 1,456 | ±3 | 82,549 | — |
| 68 |
gpt-5.1-high
|
OpenAI | 1,456 | ±4 | 41,651 | — |
| 70 |
Qwen: Qwen3.7 Plus
|
Alibaba | 1,456 | ±4 | 42,058 | — |
| 71 |
Google: Gemini 3.5 Flash Lite
|
1,455 | ±4 | 35,829 | — | |
| 53 |
deepseek-v4-pro-thinking
|
DeepSeek | 1,455 | ±4 | 44,669 | — |
| 73 |
DeepSeek-V4-Pro Preview (High)
|
DeepSeek | 1,455 | ±4 | 54,896 | — |
| 70 |
claude-sonnet-4-5-20250929
|
Anthropic | 1,455 | ±3 | 82,688 | 66 |
| 71 |
deepseek-v4-pro-high-preview
|
DeepSeek | 1,455 | ±4 | 54,902 | — |
| 73 |
grok-4.6-high
|
xAI | 1,454 | ±5 | 28,965 | — |
| 74 |
Tencent: Hy3
|
Tencent | 1,454 | ±6 | 13,220 | — |
| 75 |
OpenAI: GPT-5.6 Luna
|
OpenAI | 1,453 | ±4 | 41,426 | — |
| 75 |
gpt-5.6-luna-xhigh
|
OpenAI | 1,453 | ±4 | 41,109 | — |
| 76 |
Google: Gemma 4 31B
|
1,452 | ±7 | 6,137 | — | |
| 77 |
OpenAI: GPT-5.3 Chat
|
OpenAI | 1,450 | ±4 | 34,324 | — |
| 78 |
MoonshotAI: Kimi K2.5
|
Moonshot AI | 1,450 | ±3 | 74,744 | — |
| 79 |
kimi-k2.5-thinking
|
Moonshot AI | 1,450 | ±3 | 74,759 | — |
| 80 |
claude-opus-4-1-20250805-thinking-16k
|
Anthropic | 1,450 | ±3 | 49,542 | — |
| 80 |
ERNIE-5.0-Preview (1022)
|
Baidu | 1,449 | ±7 | 9,805 | — |
| 81 |
ernie-5.0-preview-1203
|
Baidu | 1,449 | ±6 | 9,806 | — |
| 81 | Mi Xiaomi: MiMo-V2.6-Flash | Xiaomi | 1,448 | ±6 | 13,730 | — |
| 82 |
Anthropic: Claude Opus 4.1
|
Anthropic | 1,448 | ±3 | 77,211 | 49 |
| 83 | Mi mimo-v2-pro | Xiaomi | 1,448 | ±5 | 25,435 | — |
| 84 | St StepFun: Step 5 Preview | stepfun | 1,448 | ±7 | 9,792 | — |
| 85 |
OpenAI: GPT-5.4 Mini
|
OpenAI | 1,447 | ±4 | 63,451 | — |
| 85 |
gpt-5.4-mini-high
|
OpenAI | 1,447 | ±4 | 63,449 | — |
| 86 |
ERNIE 5.0 (0110)
|
Baidu | 1,446 | ±4 | 36,481 | — |
| 86 |
ernie-5.0-0110
|
Baidu | 1,446 | ±4 | 36,487 | — |
| 87 |
Google: Gemini 2.5 Pro
|
1,445 | ±2 | 125,316 | 64 | |
| 88 |
gpt-4.5-preview
|
OpenAI | 1,445 | ±6 | 14,547 | 54 |
| 88 |
gpt-4.5-preview-2025-02-27
|
OpenAI | 1,445 | ±6 | 14,547 | — |
| 89 |
grok-4.7-xhigh
|
xAI | 1,444 | ±6 | 11,591 | — |
| 89 |
Qwen: Qwen3.6 Plus
|
Alibaba | 1,443 | ±4 | 48,142 | 78 |
| 91 |
gpt-6-luna-max
|
OpenAI | 1,443 | ±5 | 49,617 | — |
| 90 |
ChatGPT-4o Latest (20250326)
|
OpenAI | 1,443 | ±3 | 81,905 | — |
| 92 |
chatgpt-4o-latest-20250326
|
OpenAI | 1,443 | ±3 | 81,914 | — |
| 91 |
OpenAI: GPT-6 Luna
|
OpenAI | 1,442 | ±4 | 72,504 | — |
| 92 |
Qwen: Qwen3.5 397B A17B
|
Alibaba | 1,442 | ±3 | 96,206 | — |
| 93 |
SpaceXAI: Grok 4.3
|
xAI | 1,442 | ±4 | 71,348 | — |
| 94 | TM Thinking Machines: Inkling | Thinking Machines | 1,442 | ±4 | 43,705 | — |
| 95 |
Z.ai: GLM 4.7
|
Z.ai | 1,441 | ±6 | 12,245 | 68 |
| 96 |
SpaceXAI: Grok 4.7
|
xAI | 1,441 | ±6 | 14,693 | — |
| 97 |
MiniMax: MiniMax M3
|
MiniMax | 1,440 | ±4 | 67,030 | — |
| 98 |
deepseek-v4-flash-high-preview
|
DeepSeek | 1,439 | ±4 | 51,809 | — |
| 98 |
DeepSeek-V4-Flash Preview (High)
|
DeepSeek | 1,439 | ±4 | 51,781 | — |
| 99 |
OpenAI: GPT-5.1
|
OpenAI | 1,439 | ±4 | 44,419 | 73 |
| 77 |
deepseek-v4-flash-thinking
|
DeepSeek | 1,438 | ±4 | 46,445 | — |
| 100 |
Google: Gemma 4 26B A4B
|
1,438 | ±7 | 6,092 | — | |
| 102 |
gpt-5.2-high
|
OpenAI | 1,437 | ±4 | 49,655 | — |
| 102 |
Qwen: Qwen3.8 27B
|
Alibaba | 1,437 | ±5 | 26,238 | — |
| 103 | Me LongCat-Flash-Chat Exp (2602) | meituan | 1,436 | ±5 | 29,275 | — |
| 103 | Me longcat-flash-chat-2602-exp | meituan | 1,436 | ±5 | 29,291 | — |
| 104 | Re Reflection: Beam 1.0 501B A23B | reflection | 1,436 | ±9 | 4,237 | — |
| 105 |
DeepSeek: DeepSeek V4 Flash 0423
|
DeepSeek | 1,436 | ±4 | 51,982 | — |
| 106 |
OpenAI: GPT-5.2
|
OpenAI | 1,435 | ±3 | 83,828 | 79 |
| 107 |
OpenAI: GPT-5
|
OpenAI | 1,435 | ±5 | 31,712 | 77 |
| 106 |
gpt-5-high
|
OpenAI | 1,435 | ±5 | 31,722 | — |
| 108 |
qwen3-max-preview
|
Alibaba | 1,434 | ±5 | 27,367 | — |
| 109 | Mi Xiaomi: MiMo-V2.5 | Xiaomi | 1,434 | ±4 | 47,364 | — |
| 110 |
Z.ai: GLM 5V Turbo
|
Z.ai | 1,434 | ±6 | 10,477 | — |
| 111 |
Mistral: Mistral Large 4
|
Mistral | 1,434 | ±6 | 10,331 | — |
| 112 |
Google: Gemini 3.1 Flash Lite Preview
|
1,433 | ±4 | 64,209 | — | |
| 113 |
OpenAI: o3
|
OpenAI | 1,432 | ±4 | 58,894 | 72 |
| 112 |
o3-2025-04-16
|
OpenAI | 1,432 | ±4 | 58,908 | — |
| 115 | Mi mimo-v2-omni | Xiaomi | 1,431 | ±6 | 20,618 | — |
| 114 |
kimi-k2.5-instant
|
Moonshot AI | 1,431 | ±7 | 8,376 | — |
| 116 |
Grok 4.1 Fast (Reasoning)
|
xAI | 1,430 | ±3 | 57,526 | — |
| 115 |
grok-4-1-fast-reasoning
|
xAI | 1,430 | ±3 | 57,541 | — |
| 117 |
kimi-k2-thinking-turbo
|
Moonshot AI | 1,430 | ±3 | 63,348 | — |
| 119 |
Mistral: Mistral Medium 3.5
|
Mistral | 1,426 | ±6 | 11,791 | — |
| 120 |
OpenAI: GPT-5 Chat
|
OpenAI | 1,426 | ±4 | 31,183 | — |
| 119 |
claude-opus-4-20250514-thinking-16k
|
Anthropic | 1,426 | ±4 | 35,904 | — |
| 120 | Az amazon-nova-experimental-chat-26-02-10 | Amazon | 1,426 | ±10 | 3,526 | — |
| 122 |
NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
|
NVIDIA | 1,426 | ±7 | 11,557 | — |
| 121 |
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
|
NVIDIA | 1,426 | ±7 | 11,567 | — |
| 122 |
deepseek-v3.2-exp-thinking
|
DeepSeek | 1,425 | ±7 | 8,998 | — |
| 124 |
DeepSeek: DeepSeek V3.2
|
DeepSeek | 1,425 | ±3 | 48,090 | — |
| 125 |
muse-glimmer
|
Meta | 1,425 | ±10 | 3,889 | — |
| 126 |
Anthropic: Claude Haiku 5.5
|
Anthropic | 1,425 | ±8 | 6,080 | — |
| 127 |
Z.ai: GLM 4.6
|
Z.ai | 1,424 | ±4 | 35,818 | — |
| 128 |
Qwen: Qwen3 Max
|
Alibaba | 1,424 | ±6 | 9,027 | — |
| 126 |
qwen3-max-2025-09-23
|
Alibaba | 1,423 | ±6 | 9,027 | — |
| 127 |
deepseek-v3.2-thinking
|
DeepSeek | 1,422 | ±4 | 42,071 | — |
| 130 |
Qwen3-235B-A22B-Instruct (2507)
|
Alibaba | 1,422 | ±3 | 98,096 | — |
| 128 |
Qwen: Qwen3 235B A22B Instruct 2507
|
Alibaba | 1,422 | ±3 | 98,134 | — |
| 131 |
DeepSeek: DeepSeek V3.2 Exp
|
DeepSeek | 1,422 | ±6 | 11,997 | — |
| 130 |
DeepSeek: R1 0528
|
DeepSeek | 1,421 | ±6 | 18,167 | — |
| 131 |
grok-4-fast-chat
|
xAI | 1,419 | ±8 | 6,340 | — |
| 132 |
MoonshotAI: Kimi K2 0905
|
Moonshot AI | 1,419 | ±7 | 11,589 | — |
| 133 |
ernie-5.0-preview-1022
|
Baidu | 1,418 | ±9 | 4,753 | — |
| 136 |
Kimi K2 Preview (0711)
|
Moonshot AI | 1,418 | ±5 | 27,136 | — |
| 134 |
MoonshotAI: Kimi K2 0711
|
Moonshot AI | 1,418 | ±5 | 27,146 | — |
| 137 |
DeepSeek: DeepSeek V3.1
|
DeepSeek | 1,417 | ±6 | 14,607 | — |
| 138 |
Qwen: Qwen3.5-122B-A10B
|
Alibaba | 1,417 | ±4 | 29,716 | — |
| 137 |
deepseek-v3.1-terminus-thinking
|
DeepSeek | 1,416 | ±10 | 3,375 | — |
| 138 |
nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4
|
NVIDIA | 1,416 | ±12 | 2,523 | — |
| 139 |
deepseek-v3.1-thinking
|
DeepSeek | 1,416 | ±7 | 11,459 | — |
| 141 |
MiniMax: MiniMax M2.7
|
MiniMax | 1,415 | ±3 | 87,731 | — |
| 142 |
DeepSeek: DeepSeek V3.1 Terminus
|
DeepSeek | 1,415 | ±10 | 3,608 | — |
| 143 |
OpenAI: GPT-4.1
|
OpenAI | 1,415 | ±4 | 50,302 | 45 |
| 142 |
gpt-4.1-2025-04-14
|
OpenAI | 1,415 | ±4 | 50,312 | — |
| 144 |
Anthropic: Claude Haiku 4.5
|
Anthropic | 1,414 | ±2 | 152,393 | — |
| 145 |
mistral-large-3
|
Mistral | 1,414 | ±3 | 86,928 | — |
| 143 |
claude-opus-4-20250514
|
Anthropic | 1,414 | ±4 | 43,043 | 68 |
| 144 |
claude-haiku-4-5-20251001
|
Anthropic | 1,414 | ±2 | 149,199 | 67 |
| 146 |
Anthropic: Claude Opus 4
|
Anthropic | 1,414 | ±4 | 43,036 | — |
| 147 |
Qwen: Qwen3 VL 235B A22B Instruct
|
Alibaba | 1,413 | ±7 | 11,312 | — |
| 149 |
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
|
NVIDIA | 1,413 | ±9 | 4,176 | — |
| 147 | Az amazon-nova-experimental-chat-26-01-10 | Amazon | 1,413 | ±10 | 3,539 | — |
| 150 |
Grok 3 Preview (02-24)
|
xAI | 1,411 | ±4 | 32,498 | — |
| 148 |
grok-3-preview-02-24
|
xAI | 1,411 | ±4 | 32,499 | — |
| 151 |
Z.ai: GLM 4.5
|
Z.ai | 1,411 | ±5 | 23,791 | — |
| 152 |
grok-4-0709
|
xAI | 1,411 | ±4 | 39,679 | 67 |
| 153 |
Google: Gemini 2.5 Flash
|
1,409 | ±2 | 125,462 | — | |
| 152 |
hunyuan-hy3-preview
|
Tencent | 1,409 | ±7 | 6,879 | — |
| 154 |
Tencent: Hy3 preview
|
Tencent | 1,409 | ±7 | 6,875 | — |
| 155 |
Qwen: Qwen3.5-27B
|
Alibaba | 1,409 | ±4 | 28,661 | — |
| 156 |
Mistral: Mistral Medium 3.1
|
Mistral | 1,408 | ±3 | 95,285 | — |
| 157 |
Grok 4 Fast (Non-Reasoning)
|
xAI | 1,405 | ±5 | 18,267 | — |
| 155 |
grok-4-fast-reasoning
|
xAI | 1,405 | ±5 | 18,269 | — |
| 158 | TM Thinking Machines: Inkling Small | Thinking Machines | 1,405 | ±5 | 35,359 | — |
| 159 |
Gemini 2.5 Flash Preview (May 2025)
|
1,403 | ±4 | 32,982 | — | |
| 157 |
gemini-2.5-flash-preview-09-2025
|
1,403 | ±4 | 32,995 | — | |
| 158 |
o1-2024-12-17
|
OpenAI | 1,402 | ±4 | 27,807 | — |
| 160 |
OpenAI: o1
|
OpenAI | 1,402 | ±4 | 27,807 | 69 |
| 161 |
Qwen: Qwen3 235B A22B
|
Alibaba | 1,402 | ±5 | 37,485 | — |
| 159 |
qwen3-235b-a22b-no-thinking
|
Alibaba | 1,402 | ±5 | 37,484 | — |
| 160 |
claude-sonnet-4-20250514-thinking-32k
|
Anthropic | 1,402 | ±4 | 34,132 | — |
| 163 |
OpenAI: GPT-5.4 Nano
|
OpenAI | 1,401 | ±4 | 62,375 | — |
| 161 |
gpt-5.4-nano-high
|
OpenAI | 1,401 | ±4 | 62,396 | — |
| 164 | Me longcat-flash-chat | meituan | 1,401 | ±6 | 11,166 | — |
| 165 |
Qwen3-235B-A22B-Thinking (2507)
|
Alibaba | 1,400 | ±7 | 8,821 | — |
| 163 |
Qwen: Qwen3 235B A22B Thinking 2507
|
Alibaba | 1,400 | ±7 | 8,823 | — |
| 166 |
Qwen: Qwen3 Next 80B A3B Instruct
|
Alibaba | 1,398 | ±5 | 22,755 | — |
| 167 |
DeepSeek: R1
|
DeepSeek | 1,398 | ±5 | 18,524 | 75 |
| 168 |
Qwen: Qwen3.5-Flash
|
Alibaba | 1,396 | ±4 | 61,802 | — |
| 169 |
DeepSeek: DeepSeek V3
|
DeepSeek | 1,395 | ±4 | 44,974 | 62 |
| 167 |
DeepSeek: DeepSeek V3 0324
|
DeepSeek | 1,395 | ±4 | 44,973 | 64 |
| 170 |
Qwen: Qwen3 VL 235B A22B Thinking
|
Alibaba | 1,395 | ±7 | 7,855 | — |
| 171 |
hunyuan-vision-1.5-thinking
|
Tencent | 1,394 | ±12 | 2,168 | — |
| 172 |
Qwen: Qwen3.5-35B-A3B
|
Alibaba | 1,394 | ±4 | 30,443 | — |
| 174 | St StepFun: Step 3.5 Flash | stepfun | 1,393 | ±4 | 60,329 | — |
| 172 | Az amazon-nova-experimental-chat-12-10 | Amazon | 1,393 | ±9 | 3,733 | — |
| 175 | Mi mimo-v2-flash (non-thinking) | Xiaomi | 1,392 | ±3 | 48,069 | — |
| 174 |
o4-mini-2025-04-16
|
OpenAI | 1,391 | ±4 | 44,855 | — |
| 176 |
OpenAI: o4 Mini
|
OpenAI | 1,391 | ±4 | 44,851 | — |
| 175 |
claude-sonnet-4-20250514
|
Anthropic | 1,391 | ±4 | 39,163 | — |
| 177 |
Anthropic: Claude Sonnet 4
|
Anthropic | 1,391 | ±4 | 39,167 | — |
| 178 |
MiniMax: MiniMax M2.5
|
MiniMax | 1,391 | ±4 | 42,791 | — |
| 177 |
gpt-5-mini-high
|
OpenAI | 1,390 | ±5 | 26,804 | — |
| 179 |
OpenAI: GPT-5 Mini
|
OpenAI | 1,390 | ±5 | 26,799 | 66 |
| 180 |
o1-preview
|
OpenAI | 1,389 | ±5 | 31,122 | — |
| 179 |
claude-3-7-sonnet-20250219-thinking-32k
|
Anthropic | 1,388 | ±4 | 38,159 | — |
| 182 |
Qwen3-Coder-480B-A35B-Instruct
|
Alibaba | 1,388 | ±5 | 25,192 | — |
| 183 |
Upstage: Solar Pro 4
|
Upstage | 1,387 | ±5 | 24,453 | — |
| 184 |
Mistral: Mistral Medium 3
|
Mistral | 1,387 | ±5 | 32,776 | — |
| 185 |
Hunyuan T1 (20250711)
|
Tencent | 1,387 | ±9 | 4,595 | — |
| 182 |
hunyuan-t1-20250711
|
Tencent | 1,387 | ±9 | 4,595 | — |
| 183 |
solar-pro4
|
Upstage | 1,386 | ±5 | 21,281 | — |
| 186 | Mi mimo-v2-flash (thinking) | Xiaomi | 1,386 | ±6 | 11,140 | — |
| 187 |
minimax-m2.1-preview
|
MiniMax | 1,385 | ±5 | 17,230 | — |
| 188 |
Hunyuan TurboS (20250226)
|
Tencent | 1,383 | ±6 | 10,623 | — |
| 186 |
hunyuan-turbos-20250416
|
Tencent | 1,383 | ±6 | 10,626 | — |
| 187 |
gpt-4.1-mini-2025-04-14
|
OpenAI | 1,383 | ±4 | 38,709 | — |
| 189 |
OpenAI: GPT-4.1 Mini
|
OpenAI | 1,383 | ±4 | 38,701 | — |
| 188 |
Qwen: Qwen3 30B A3B Instruct 2507
|
Alibaba | 1,382 | ±5 | 23,322 | — |
| 190 |
Qwen3-30B-A3B-Instruct (2507)
|
Alibaba | 1,382 | ±5 | 23,306 | — |
| 191 |
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
|
1,379 | ±3 | 47,420 | — | |
| 189 |
gemini-2.5-flash-lite-preview-09-2025-no-thinking
|
1,379 | ±3 | 47,437 | — | |
| 192 | TL trinity-large-preview | Unknown | 1,379 | ±4 | 31,246 | — |
| 193 |
Z.ai: GLM 4.6V
|
Z.ai | 1,378 | ±11 | 2,831 | — |
| 193 |
gemini-2.5-flash-lite-preview-06-17-thinking
|
1,375 | ±5 | 32,381 | — | |
| 194 |
claude-3-5-sonnet-20241022
|
Anthropic | 1,374 | ±3 | 87,769 | 45 |
| 196 |
Claude 3.5 Sonnet (October 2024)
|
Anthropic | 1,374 | ±3 | 87,771 | — |
| 197 |
qwen2.5-max
|
Alibaba | 1,374 | ±4 | 32,487 | — |
| 198 |
Z.ai: GLM 4.5 Air
|
Z.ai | 1,373 | ±4 | 30,646 | — |
| 197 |
claude-3-7-sonnet-20250219
|
Anthropic | 1,373 | ±4 | 42,572 | 74 |
| 199 |
Claude 3.7 Sonnet (Thinking)
|
Anthropic | 1,372 | ±4 | 42,572 | — |
| 200 |
Qwen: Qwen3 Next 80B A3B Thinking
|
Alibaba | 1,369 | ±6 | 13,473 | — |
| 201 | AA Arcee AI: Trinity Large Thinking | arcee-ai | 1,367 | ±5 | 30,307 | — |
| 202 |
Google: Gemma 3 27B
|
1,365 | ±4 | 46,665 | 47 | |
| 203 |
Z.ai: GLM 4.7 Flash
|
Z.ai | 1,365 | ±6 | 12,013 | — |
| 204 | Az amazon-nova-experimental-chat (10-09) | Amazon | 1,364 | ±4 | 26,031 | — |
| 205 |
MiniMax: MiniMax M1
|
MiniMax | 1,364 | ±4 | 34,299 | — |
| 203 | Az amazon-nova-experimental-chat-11-10 | Amazon | 1,364 | ±4 | 26,039 | — |
| 204 |
grok-3-mini-high
|
xAI | 1,364 | ±5 | 15,596 | — |
| 206 |
Grok 3 Mini (High)
|
xAI | 1,364 | ±5 | 15,591 | — |
| 205 |
OpenAI: o3 Mini High
|
OpenAI | 1,364 | ±5 | 18,589 | — |
| 208 |
nvidia-nemotron-3-super-120b-a12b
|
NVIDIA | 1,360 | ±7 | 7,869 | — |
| 209 |
Gemini 2.0 Flash (001)
|
1,360 | ±4 | 43,443 | — | |
| 207 | GD gemini-2.0-flash-001 | Google DeepMind,Google | 1,360 | ±4 | 43,446 | 61 |
| 211 |
grok-3-mini-beta
|
xAI | 1,358 | ±5 | 20,929 | — |
| 210 |
mistral-small-2506
|
Mistral | 1,356 | ±5 | 17,462 | — |
| 212 |
Mistral Small 3.2 (2506)
|
Mistral | 1,356 | ±5 | 17,454 | — |
| 213 | I3 intellect-3 | Unknown | 1,356 | ±8 | 5,432 | — |
| 214 |
Cohere: Command A
|
Cohere | 1,354 | ±3 | 55,758 | — |
| 215 |
Gemini 2.0 Flash-Lite Preview (02-05)
|
1,354 | ±4 | 24,955 | — | |
| 213 |
gemini-2.0-flash-lite-preview-02-05
|
1,354 | ±4 | 24,955 | — | |
| 216 |
NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
|
NVIDIA | 1,353 | ±5 | 22,498 | — |
| 217 |
Z.ai: GLM 4.5V
|
Z.ai | 1,352 | ±8 | 4,821 | — |
| 218 |
OpenAI: gpt-oss-120b
|
OpenAI | 1,352 | ±4 | 30,207 | 61 |
| 216 |
nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4
|
NVIDIA | 1,351 | ±6 | 19,938 | — |
| 217 |
gemini-1.5-pro-002
|
1,351 | ±3 | 55,606 | — | |
| 220 | St step-3 | stepfun | 1,349 | ±8 | 6,295 | — |
| 219 |
hunyuan-turbos-20250226
|
Tencent | 1,349 | ±12 | 2,220 | — |
| 223 |
OpenAI: o3 Mini
|
OpenAI | 1,348 | ±4 | 56,742 | 86 |
| 221 | Az amazon-nova-experimental-chat-10-20 | Amazon | 1,348 | ±6 | 11,626 | — |
| 224 |
llama-3.1-nemotron-ultra-253b-v1
|
NVIDIA | 1,348 | ±12 | 2,549 | — |
| 225 |
Qwen: Qwen3 32B
|
Alibaba | 1,347 | ±9 | 3,926 | — |
| 224 | Az amazon-nova-experimental-chat-10-09 | Amazon | 1,346 | ±11 | 2,781 | — |
| 225 |
OpenAI: GPT-4o (2024-05-13)
|
OpenAI | 1,346 | ±3 | 112,881 | — |
| 227 |
OpenAI: GPT-4o
|
OpenAI | 1,346 | ±3 | 112,881 | 27 |
| 228 |
Qwen: Qwen-Plus
|
Alibaba | 1,346 | ±8 | 5,819 | — |
| 226 |
qwen-plus-0125
|
Alibaba | 1,346 | ±8 | 5,819 | — |
| 229 |
MiniMax: MiniMax M2
|
MiniMax | 1,344 | ±8 | 6,855 | — |
| 230 | AG ling-flash-2.0 | ant-group | 1,343 | ±7 | 6,953 | — |
| 228 |
claude-3-5-sonnet-20240620
|
Anthropic | 1,343 | ±3 | 82,419 | — |
| 232 |
Llama 3.3 Nemotron Super 49B v1.5
|
NVIDIA | 1,343 | ±10 | 3,328 | — |
| 233 | In Inception: Mercury 2 | inception | 1,343 | ±11 | 3,193 | — |
| 231 |
nvidia-llama-3.3-nemotron-super-49b-v1.5
|
NVIDIA | 1,343 | ±10 | 3,328 | — |
| 232 |
glm-4-plus-0111
|
Z.ai | 1,343 | ±8 | 5,760 | — |
| 235 |
Google: Gemma 3 12B
|
1,342 | ±10 | 3,829 | — | |
| 236 |
Hunyuan Turbo (0110)
|
Tencent | 1,341 | ±12 | 2,290 | — |
| 234 |
hunyuan-turbo-0110
|
Tencent | 1,341 | ±12 | 2,290 | — |
| 237 |
granite-4.2-30b
|
IBM | 1,340 | ±10 | 3,407 | — |
| 238 |
OpenAI: GPT-5 Nano
|
OpenAI | 1,338 | ±7 | 8,134 | 67 |
| 236 |
gpt-5-nano-high
|
OpenAI | 1,338 | ±7 | 8,132 | — |
| 239 |
o1-mini
|
OpenAI | 1,337 | ±4 | 51,981 | 64 |
| 238 |
gemini-advanced-0514
|
1,336 | ±5 | 50,148 | — | |
| 240 |
Gemini Advanced (0514)
|
1,336 | ±5 | 50,148 | — | |
| 241 |
Grok 2 (2024-08-13)
|
xAI | 1,336 | ±4 | 63,498 | — |
| 239 |
grok-2-2024-08-13
|
xAI | 1,336 | ±4 | 63,498 | — |
| 242 |
QwQ-32B
|
Alibaba | 1,336 | ±4 | 25,174 | 69 |
| 240 |
OpenAI: GPT-4o (2024-08-06)
|
OpenAI | 1,336 | ±4 | 45,499 | — |
| 242 |
llama-3.1-405b-instruct-bf16
|
Meta | 1,336 | ±4 | 41,375 | — |
| 245 | Az Amazon Nova 2 Lite | Amazon | 1,335 | ±6 | 12,410 | — |
| 243 | Az Amazon: Nova 2 Lite | Amazon | 1,335 | ±6 | 12,413 | — |
| 244 |
llama-3.1-405b-instruct-fp8
|
Meta | 1,334 | ±4 | 59,656 | — |
| 246 |
Llama-3.1-405B-Instruct
|
Meta | 1,334 | ±4 | 59,656 | — |
| 247 | St Step-2 16K Exp (202412) | stepfun | 1,334 | ±9 | 4,833 | — |
| 245 | St step-2-16k-exp-202412 | stepfun | 1,333 | ±9 | 4,833 | — |
| 248 | A2 olmo-3.1-32b-instruct | Allen Institute for AI | 1,329 | ±6 | 11,805 | — |
| 249 | YL yi-lightning | Unknown | 1,328 | ±5 | 27,332 | — |
| 250 |
Llama 3.3 Nemotron Super 49B v1
|
NVIDIA | 1,328 | ±12 | 2,218 | — |
| 248 |
llama-3.3-nemotron-49b-super-v1
|
NVIDIA | 1,328 | ±12 | 2,218 | — |
| 251 |
llama-4-maverick-17b-128e-instruct
|
Meta | 1,327 | ±4 | 39,444 | — |
| 252 |
Qwen: Qwen3 30B A3B
|
Alibaba | 1,327 | ±5 | 26,155 | — |
| 253 |
Hunyuan Large (2025-02-10)
|
Tencent | 1,326 | ±10 | 3,738 | — |
| 251 |
hunyuan-large-2025-02-10
|
Tencent | 1,326 | ±10 | 3,738 | — |
| 252 |
claude-3-5-haiku-20241022
|
Anthropic | 1,325 | ±3 | 69,061 | 30 |
| 254 |
Claude 3.5 Haiku (20241022)
|
Anthropic | 1,325 | ±3 | 69,055 | — |
| 253 |
gpt-4-turbo-2024-04-09
|
OpenAI | 1,325 | ±4 | 98,114 | — |
| 255 |
OpenAI: GPT-4 Turbo
|
OpenAI | 1,324 | ±4 | 98,114 | — |
| 254 |
gemini-1.5-pro-001
|
1,324 | ±4 | 79,138 | — | |
| 256 |
Gemini 1.5 Pro (001)
|
1,324 | ±4 | 79,138 | — | |
| 255 |
deepseek-v2.5-1210
|
DeepSeek | 1,323 | ±8 | 6,795 | — |
| 258 | AG ring-flash-2.0 | ant-group | 1,322 | ±7 | 6,987 | — |
| 257 |
claude-3-opus-20240229
|
Anthropic | 1,322 | ±3 | 194,909 | 32 |
| 258 |
gpt-4.1-nano-2025-04-14
|
OpenAI | 1,322 | ±8 | 6,103 | — |
| 259 |
OpenAI: GPT-4.1 Nano
|
OpenAI | 1,322 | ±8 | 6,103 | — |
| 260 |
Claude 3 Opus (20240229)
|
Anthropic | 1,322 | ±3 | 194,909 | — |
| 261 | A2 molmo-2-8b | Allen Institute for AI | 1,322 | ±21 | 823 | — |
| 262 |
Llama-4-Scout-17B-16E-Instruct
|
Meta | 1,322 | ±5 | 29,830 | — |
| 263 | St Step-1o Turbo (202506) | stepfun | 1,320 | ±7 | 8,904 | — |
| 261 | St step-1o-turbo-202506 | stepfun | 1,320 | ±7 | 8,901 | — |
| 264 |
glm-4-plus
|
Z.ai | 1,319 | ±5 | 26,126 | — |
| 265 |
qwen-max
|
Alibaba | 1,318 | ±6 | 16,478 | — |
| 263 |
qwen-max-0919
|
Alibaba | 1,318 | ±6 | 16,478 | — |
| 266 |
Meta: Llama 3.3 70B Instruct
|
Meta | 1,318 | ±4 | 54,493 | 34 |
| 267 |
OpenAI: GPT-4o-mini
|
OpenAI | 1,318 | ±4 | 68,705 | 31 |
| 265 |
OpenAI: GPT-4o-mini (2024-07-18)
|
OpenAI | 1,318 | ±4 | 68,705 | — |
| 268 |
Google: Gemma 3n 4B
|
1,318 | ±5 | 22,142 | — | |
| 269 |
OpenAI: gpt-oss-20b
|
OpenAI | 1,317 | ±6 | 10,417 | 41 |
| 270 |
Qwen2.5-Plus (1127)
|
Alibaba | 1,315 | ±6 | 10,187 | — |
| 268 |
qwen2.5-plus-1127
|
Alibaba | 1,315 | ±6 | 10,187 | — |
| 269 |
Mistral Large 2407
|
Mistral | 1,314 | ±4 | 45,459 | — |
| 271 |
Mistral Large 2 (2407)
|
Mistral | 1,314 | ±4 | 45,459 | — |
| 272 | AV athene-v2-chat | Unknown | 1,314 | ±5 | 24,739 | — |
| 273 |
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
|
NVIDIA | 1,314 | ±5 | 15,765 | — |
| 271 |
nvidia-nemotron-3-nano-30b-a3b-bf16
|
NVIDIA | 1,314 | ±5 | 15,770 | — |
| 272 |
gpt-4-0125-preview
|
OpenAI | 1,313 | ±4 | 93,439 | — |
| 273 |
gpt-4-1106-preview
|
OpenAI | 1,313 | ±4 | 100,105 | — |
| 275 |
OpenAI: GPT-4 Turbo Preview
|
OpenAI | 1,313 | ±4 | 100,105 | — |
| 276 |
Hunyuan Standard (2025-02-10)
|
Tencent | 1,311 | ±10 | 3,904 | — |
| 274 |
hunyuan-standard-2025-02-10
|
Tencent | 1,311 | ±10 | 3,904 | — |
| 275 |
gemini-1.5-flash-002
|
1,309 | ±4 | 34,902 | — | |
| 278 |
Grok 2 mini (2024-08-13)
|
xAI | 1,308 | ±4 | 52,567 | — |
| 276 |
grok-2-mini-2024-08-13
|
xAI | 1,308 | ±4 | 52,567 | — |
| 279 |
deepseek-v2.5
|
DeepSeek | 1,307 | ±5 | 24,572 | — |
| 278 | A7 athene-70b-0725 | Unknown | 1,307 | ±6 | 19,621 | — |
| 280 | A7 Athene 70B (0725) | Unknown | 1,307 | ±6 | 19,621 | — |
| 281 | A2 AllenAI: Olmo 3 32B Think | Allen Institute for AI | 1,306 | ±8 | 5,825 | — |
| 282 | IA mercury | inception-ai | 1,306 | ±14 | 1,964 | — |
| 280 |
mistral-large-2411
|
Mistral | 1,306 | ±4 | 28,073 | 37 |
| 282 |
magistral-medium-2506
|
Mistral | 1,305 | ±6 | 11,510 | — |
| 284 |
Magistral Medium (2506)
|
Mistral | 1,305 | ±6 | 11,509 | — |
| 285 |
IBM: Granite 4.1 8B
|
IBM | 1,304 | ±10 | 4,177 | — |
| 286 |
Google: Gemma 3 4B
|
1,303 | ±9 | 4,171 | — | |
| 287 |
Qwen2.5 72B Instruct
|
Alibaba | 1,303 | ±4 | 39,406 | — |
| 288 |
Mistral Small 3.1 24B Instruct (2503)
|
Mistral | 1,303 | ±5 | 32,721 | — |
| 286 |
mistral-small-3.1-24b-instruct-2503
|
Mistral | 1,303 | ±5 | 32,727 | — |
| 289 |
llama-3.1-nemotron-70b-instruct
|
NVIDIA | 1,299 | ±8 | 7,140 | — |
| 290 |
hunyuan-large-vision
|
Tencent | 1,294 | ±9 | 5,283 | — |
| 291 |
Meta: Llama 3.1 70B Instruct
|
Meta | 1,293 | ±4 | 55,240 | — |
| 292 |
granite-4.2-3b
|
IBM | 1,290 | ±12 | 3,260 | — |
| 293 | Az Amazon Nova Pro 1.0 | Amazon | 1,290 | ±5 | 24,745 | — |
| 291 | Az amazon.nova-pro-v1:0 | Amazon | 1,290 | ±5 | 24,745 | — |
| 294 |
IBM: Granite 4.2 8B
|
IBM | 1,290 | ±11 | 3,259 | — |
| 295 |
Google: Gemma 2 27B
|
1,290 | ±3 | 75,754 | 21 | |
| 296 | J1 jamba-1.5-large | Unknown | 1,289 | ±7 | 8,662 | — |
| 295 | Re reka-core-20240904 | Reka AI | 1,288 | ±7 | 7,312 | — |
| 297 | Re Reka Core (20240904) | Reka AI | 1,288 | ±7 | 7,312 | — |
| 296 |
gpt-4-0314
|
OpenAI | 1,288 | ±5 | 54,173 | — |
| 299 |
Granite-4.0-H-Small
|
IBM | 1,288 | ±8 | 5,628 | — |
| 297 |
ibm-granite-h-small
|
IBM | 1,287 | ±8 | 5,630 | — |
| 300 |
llama-3.1-nemotron-51b-instruct
|
NVIDIA | 1,287 | ±10 | 3,749 | — |
| 300 |
gemini-1.5-flash-001
|
1,287 | ±4 | 62,833 | — | |
| 301 |
Gemini 1.5 Flash (001)
|
1,287 | ±4 | 62,833 | — | |
| 302 | A2 olmo-3.1-32b-think | Allen Institute for AI | 1,286 | ±7 | 8,299 | — |
| 303 | A2 llama-3.1-tulu-3-70b | Allen Institute for AI | 1,286 | ±10 | 2,846 | — |
| 302 |
claude-3-sonnet-20240229
|
Anthropic | 1,281 | ±4 | 109,284 | — |
| 304 |
Claude 3 Sonnet (20240229)
|
Anthropic | 1,281 | ±4 | 109,284 | — |
| 305 |
gemma-2-9b-it-simpo
|
1,280 | ±7 | 10,072 | — | |
| 306 |
nemotron-4-340b-instruct
|
NVIDIA | 1,277 | ±5 | 19,659 | — |
| 307 |
llama-3-70b-instruct
|
Meta | 1,277 | ±4 | 156,876 | — |
| 306 |
Cohere: Command R+ (08-2024)
|
Cohere | 1,276 | ±7 | 9,866 | — |
| 307 |
gpt-4-0613
|
OpenAI | 1,276 | ±4 | 88,723 | — |
| 309 |
OpenAI: GPT-4
|
OpenAI | 1,276 | ±4 | 88,723 | — |
| 308 |
Mistral: Mistral Small 3
|
Mistral | 1,274 | ±6 | 14,681 | — |
| 310 |
Mistral Small 24B Instruct (2501)
|
Mistral | 1,274 | ±6 | 14,681 | — |
| 309 |
glm-4-0520
|
Z.ai | 1,273 | ±7 | 9,788 | — |
| 311 |
GLM-4 (0520)
|
Z.ai | 1,273 | ±7 | 9,788 | — |
| 310 | Re reka-flash-20240904 | Reka AI | 1,272 | ±7 | 7,536 | — |
| 312 | Re Reka Flash (20240904) | Reka AI | 1,272 | ±7 | 7,536 | — |
| 313 |
Qwen2.5 Coder 32B Instruct
|
Alibaba | 1,271 | ±8 | 5,432 | — |
| 312 |
c4ai-aya-expanse-32b
|
Cohere | 1,267 | ±5 | 27,124 | — |
| 314 |
Aya Expanse 32B
|
Cohere | 1,267 | ±5 | 27,124 | — |
| 315 |
gemma-2-9b-it
|
1,267 | ±4 | 54,611 | 13 | |
| 316 |
deepseek-coder-v2
|
DeepSeek | 1,265 | ±6 | 15,147 | — |
| 316 |
command-r-plus
|
Cohere | 1,262 | ±4 | 77,554 | — |
| 317 |
qwen2-72b-instruct
|
Alibaba | 1,262 | ±5 | 37,325 | — |
| 318 |
Cohere: Command R (08-2024)
|
Cohere | 1,262 | ±4 | 77,554 | — |
| 319 |
Anthropic: Claude 3 Haiku
|
Anthropic | 1,262 | ±4 | 117,701 | — |
| 320 | Az Amazon Nova Lite 1.0 | Amazon | 1,260 | ±5 | 19,372 | — |
| 318 | Az amazon.nova-lite-v1:0 | Amazon | 1,260 | ±5 | 19,372 | — |
| 319 |
gemini-1.5-flash-8b-001
|
1,259 | ±4 | 35,558 | — | |
| 321 |
Gemini 1.5 Flash-8B (001)
|
1,259 | ±4 | 35,558 | — | |
| 322 |
Microsoft: Phi 4
|
Microsoft | 1,256 | ±5 | 24,126 | 41 |
| 321 | A2 olmo-2-0325-32b-instruct | Allen Institute for AI | 1,252 | ±11 | 3,334 | — |
| 323 | A2 OLMo 2 32B Instruct (0325) | Allen Institute for AI | 1,252 | ±11 | 3,334 | — |
| 323 |
mistral-large-2402
|
Mistral | 1,243 | ±5 | 62,436 | — |
| 325 |
Mistral Large
|
Mistral | 1,243 | ±5 | 62,436 | — |
| 326 | Az Amazon Nova Micro 1.0 | Amazon | 1,241 | ±5 | 19,364 | — |
| 324 | Az amazon.nova-micro-v1:0 | Amazon | 1,241 | ±5 | 19,364 | — |
| 327 | J1 jamba-1.5-mini | Unknown | 1,240 | ±7 | 8,858 | — |
| 326 |
ministral-8b-2410
|
Mistral | 1,238 | ±9 | 4,781 | — |
| 328 |
Mistral: Ministral 8B
|
Mistral | 1,238 | ±9 | 4,781 | — |
| 327 |
gemini-pro-dev-api
|
1,237 | ±7 | 18,354 | — | |
| 329 |
gemini-pro
|
1,237 | ±7 | 18,354 | — | |
| 330 |
qwen1.5-110b-chat
|
Alibaba | 1,234 | ±6 | 26,195 | — |
| 329 | Re reka-flash-21b-20240226-online | Reka AI | 1,234 | ±7 | 15,450 | — |
| 332 |
qwen1.5-72b-chat
|
Alibaba | 1,234 | ±5 | 39,302 | — |
| 333 |
hunyuan-standard-256k
|
Tencent | 1,233 | ±12 | 2,728 | — |
| 334 |
mixtral-8x22b-instruct-v0.1
|
Mistral | 1,230 | ±5 | 51,416 | — |
| 334 | Re reka-flash-21b-20240226 | Reka AI | 1,227 | ±6 | 24,806 | — |
| 336 | Re Reka Flash 21B (20240226) | Reka AI | 1,227 | ±6 | 24,806 | — |
| 335 |
gpt-3.5-turbo-0125
|
OpenAI | 1,226 | ±5 | 66,207 | — |
| 337 |
OpenAI: GPT-3.5 Turbo
|
OpenAI | 1,226 | ±5 | 66,207 | — |
| 338 |
llama-3-8b-instruct
|
Meta | 1,224 | ±4 | 104,642 | — |
| 338 |
c4ai-aya-expanse-8b
|
Cohere | 1,223 | ±7 | 9,818 | — |
| 340 |
Aya Expanse 8B
|
Cohere | 1,223 | ±7 | 9,818 | — |
| 341 |
mistral-medium
|
Mistral | 1,223 | ±5 | 34,550 | — |
| 342 | A2 llama-3.1-tulu-3-8b | Allen Institute for AI | 1,221 | ±11 | 2,896 | — |
| 343 | ZO zephyr-orpo-141b-A35b-v0.1 | Unknown | 1,213 | ±11 | 4,652 | — |
| 344 | 0A Yi-1.5-34B-Chat | 01.AI | 1,213 | ±5 | 24,146 | — |
| 345 |
Meta: Llama 3.1 8B Instruct
|
Meta | 1,211 | ±4 | 49,605 | — |
| 346 |
granite-3.1-8b-instruct
|
IBM | 1,209 | ±11 | 3,090 | — |
| 345 |
gpt-3.5-turbo-1106
|
OpenAI | 1,204 | ±9 | 16,619 | — |
| 348 |
qwen1.5-32b-chat
|
Alibaba | 1,204 | ±6 | 21,741 | — |
| 349 |
gemma-2-2b-it
|
1,200 | ±4 | 46,616 | — | |
| 350 |
phi-3-medium-4k-instruct
|
Microsoft | 1,198 | ±5 | 25,055 | — |
| 351 |
Mixtral-8x7B-Instruct-v0.1
|
Mistral | 1,197 | ±4 | 73,503 | — |
| 352 | DI dbrx-instruct-preview | Unknown | 1,196 | ±6 | 32,191 | — |
| 353 |
qwen1.5-14b-chat
|
Alibaba | 1,191 | ±7 | 17,839 | — |
| 354 | I5 internlm2_5-20b-chat | Unknown | 1,191 | ±7 | 9,901 | — |
| 355 |
deepseek-llm-67b-chat
|
DeepSeek | 1,185 | ±11 | 4,932 | — |
| 356 |
wizardlm-70b
|
Microsoft | 1,185 | ±9 | 8,214 | — |
| 357 | 0A Yi-34B-Chat | 01.AI | 1,184 | ±7 | 15,483 | — |
| 358 |
granite-3.0-8b-instruct
|
IBM | 1,183 | ±9 | 6,638 | — |
| 358 | O3 openchat-3.5-0106 | Unknown | 1,183 | ±8 | 12,637 | — |
| 360 | O3 openchat-3.5 | Unknown | 1,183 | ±8 | 12,637 | — |
| 361 |
gemma-1.1-7b-it
|
1,183 | ±6 | 23,893 | — | |
| 362 |
snowflake-arctic-instruct
|
Snowflake | 1,180 | ±6 | 32,832 | — |
| 363 |
granite-3.1-2b-instruct
|
IBM | 1,179 | ±11 | 3,188 | — |
| 364 | T2 tulu-2-dpo-70b | Unknown | 1,178 | ±10 | 6,535 | — |
| 365 | O2 openhermes-2.5-mistral-7b | Unknown | 1,176 | ±10 | 5,006 | — |
| 366 | V3 vicuna-33b | Unknown | 1,173 | ±6 | 22,479 | — |
| 367 |
Phi-3-small-8k-instruct
|
Microsoft | 1,171 | ±6 | 17,766 | — |
| 368 | SL starling-lm-7b-beta | Unknown | 1,171 | ±7 | 16,056 | — |
| 369 |
llama-2-70b-chat
|
Meta | 1,171 | ±5 | 38,492 | — |
| 370 | SL starling-lm-7b-alpha | Unknown | 1,167 | ±8 | 10,224 | — |
| 371 |
Meta: Llama 3.2 3B Instruct
|
Meta | 1,167 | ±8 | 7,936 | — |
| 372 |
nous-hermes-2-mixtral-8x7b-dpo
|
Nous Research | 1,164 | ±12 | 3,777 | — |
| 373 |
granite-3.0-2b-instruct
|
IBM | 1,157 | ±8 | 6,837 | — |
| 372 |
llama2-70b-steerlm-chat
|
NVIDIA | 1,155 | ±13 | 3,585 | — |
| 374 |
Llama 2 70B SteerLM Chat
|
NVIDIA | 1,155 | ±13 | 3,585 | — |
| 375 |
QwQ-32B-Preview
|
Alibaba | 1,154 | ±11 | 3,231 | — |
| 376 |
solar-10.7b-instruct-v1.0
|
Upstage | 1,152 | ±13 | 4,155 | — |
| 377 | D2 dolphin-2.2.1-mistral-7b | Unknown | 1,152 | ±15 | 1,679 | — |
| 378 | M3 mpt-30b-chat | Unknown | 1,151 | ±12 | 2,572 | — |
| 379 |
wizardlm-13b
|
Microsoft | 1,150 | ±9 | 7,044 | — |
| 380 |
mistral-7b-instruct-v0.2
|
Mistral | 1,149 | ±7 | 19,402 | — |
| 381 | F1 falcon-180b-chat | Unknown | 1,148 | ±17 | 1,295 | — |
| 382 |
qwen1.5-7b-chat
|
Alibaba | 1,144 | ±10 | 4,737 | — |
| 381 |
phi-3-mini-4k-instruct-june-2024
|
Microsoft | 1,143 | ±6 | 12,297 | — |
| 384 | V1 vicuna-13b | Unknown | 1,142 | ±7 | 19,367 | — |
| 385 |
llama-2-13b-chat
|
Meta | 1,141 | ±7 | 19,174 | — |
| 386 |
qwen-14b-chat
|
Alibaba | 1,139 | ±11 | 4,964 | — |
| 387 |
palm-2
|
1,139 | ±9 | 8,554 | — | |
| 388 |
gemma-7b-it
|
1,138 | ±9 | 8,925 | — | |
| 387 |
codellama-34b-instruct
|
Meta | 1,137 | ±9 | 7,366 | — |
| 389 |
Code Llama 34B Instruct
|
Meta | 1,137 | ±9 | 7,366 | — |
| 390 | Z7 zephyr-7b-beta | Unknown | 1,131 | ±9 | 11,118 | — |
| 391 |
phi-3-mini-128k-instruct
|
Microsoft | 1,130 | ±7 | 20,685 | — |
| 392 |
Phi-3-mini-4k-instruct
|
Microsoft | 1,128 | ±6 | 20,118 | — |
| 393 | G3 guanaco-33b | Unknown | 1,128 | ±12 | 2,921 | — |
| 394 | Z7 zephyr-7b-alpha | Unknown | 1,127 | ±16 | 1,785 | — |
| 395 | SN stripedhyena-nous-7b | Unknown | 1,122 | ±11 | 5,182 | — |
| 394 |
codellama-70b-instruct
|
Meta | 1,119 | ±18 | 1,143 | — |
| 396 |
Code Llama 70B Instruct
|
Meta | 1,119 | ±18 | 1,143 | — |
| 397 |
gemma-1.1-2b-it
|
1,117 | ±8 | 10,854 | — | |
| 398 | V7 vicuna-7b | Unknown | 1,115 | ±9 | 6,923 | — |
| 399 | S1 smollm2-1.7b-instruct | Unknown | 1,115 | ±14 | 2,199 | — |
| 400 |
Meta: Llama 3.2 1B Instruct
|
Meta | 1,111 | ±8 | 8,045 | — |
| 401 |
mistral-7b-instruct
|
Mistral | 1,110 | ±9 | 8,977 | — |
| 402 |
llama-2-7b-chat
|
Meta | 1,108 | ±7 | 14,148 | — |
| 403 |
gemma-2b-it
|
1,094 | ±11 | 4,780 | — | |
| 404 |
qwen1.5-4b-chat
|
Alibaba | 1,091 | ±9 | 7,597 | — |
| 405 | A2 olmo-7b-instruct | Allen Institute for AI | 1,074 | ±11 | 6,328 | — |
| 406 | K1 koala-13b | Unknown | 1,071 | ±10 | 6,965 | — |
| 407 | A1 alpaca-13b | Unknown | 1,070 | ±11 | 5,745 | — |
| 408 | G1 gpt4all-13b-snoozy | Unknown | 1,068 | ±15 | 1,743 | — |
| 409 | M7 mpt-7b-chat | Unknown | 1,064 | ±12 | 3,924 | — |
| 410 | C6 chatglm3-6b | Unknown | 1,057 | ±12 | 4,658 | — |
| 411 | R4 RWKV-4-Raven-14B | Unknown | 1,042 | ±11 | 4,845 | — |
| 412 | C6 chatglm2-6b | Unknown | 1,025 | ±14 | 2,658 | — |
| 411 | OP oasst-pythia-12b | Unknown | 1,024 | ±11 | 6,310 | — |
| 413 | OP OpenAssistant Pythia 12B | Unknown | 1,024 | ±11 | 6,310 | — |
| 414 |
chatglm-6b
|
Z.ai | 996 | ±12 | 4,914 | — |
| 415 | FT fastchat-t5-3b | Unknown | 993 | ±12 | 4,203 | — |
| 414 | DV dolly-v2-12b | Unknown | 983 | ±13 | 3,412 | — |
| 416 | D2 Dolly 2.0 12B | Unknown | 983 | ±13 | 3,412 | — |
| 417 |
llama-13b
|
Meta | 975 | ±16 | 2,391 | — |
| 418 | ST stablelm-tuned-alpha-7b | Unknown | 953 | ±13 | 3,287 | — |
The Known Good
How to read Elo. A rating is only meaningful against the population that produced it: a model's number in one
arena cannot be compared to its number in another, and a rating built on a few hundred votes moves far more than one
built on tens of thousands — the 95% confidence interval is the honest guide to that. Elo measures which output a
person preferred, not whether it was correct; for correctness see the
evaluations and the
Known Good Index, which does not include Elo. Ratings are
ingested from Arena and are published under the source's own terms — see
attribution.