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.
12 of 381 models ▾
☰⚙⇩
+Add model from specific provider
The Known Good
Text Arena — full ranking
381 models rated
11,014,768 votes countedRatings captured 25 Jul 2026 Source: Arena
| # | Model | Creator | Elo | 95% CI | Votes | Known Good Index |
|---|---|---|---|---|---|---|
| 1 |
claude-opus-4-6-thinking
|
Anthropic | 1,503 | ±4 | 63,191 | — |
| 2 |
Anthropic: Claude Opus 4.6
|
Anthropic | 1,497 | ±4 | 67,037 | 88 |
| 3 |
Anthropic: Claude Fable 5
|
Anthropic | 1,493 | ±6 | 14,646 | — |
| 7 |
Google: Gemini 3.6 Flash
|
1,491 | ±9 | 4,747 | — | |
| 8 |
gemini-3.5-flash-high
|
1,490 | ±6 | 10,092 | — | |
| 4 |
claude-opus-4-7-thinking
|
Anthropic | 1,489 | ±4 | 50,683 | — |
| 11 |
qwen3.7-max-preview
|
Alibaba | 1,485 | ±10 | 3,714 | — |
| 5 |
Meta: Muse Spark 1.1
|
Meta | 1,483 | ±7 | 7,927 | — |
| 6 |
Anthropic: Claude Opus 4.7
|
Anthropic | 1,482 | ±4 | 51,788 | 94 |
| 9 |
Gemini 3 Pro
|
1,480 | ±4 | 41,268 | — | |
| 10 |
Google: Gemini 3.1 Pro Preview
|
1,479 | ±4 | 84,631 | 96 | |
| 12 |
gemini-3.5-flash-medium
|
1,475 | ±6 | 14,063 | — | |
| 13 |
MoonshotAI: Kimi K3
|
Moonshot AI | 1,473 | ±10 | 3,619 | — |
| 14 |
gpt-5.5-instant
|
OpenAI | 1,473 | ±8 | 25,995 | — |
| 14 |
muse-spark
|
Meta | 1,473 | ±6 | 13,565 | — |
| 15 |
qwen3.5-max-preview
|
Alibaba | 1,470 | ±5 | 21,479 | — |
| 16 |
gpt-5.4-high
|
OpenAI | 1,470 | ±4 | 58,997 | — |
| 17 |
gpt-5.5-high
|
OpenAI | 1,469 | ±4 | 45,760 | — |
| 18 |
ernie-5.1
|
Baidu | 1,467 | ±5 | 37,418 | — |
| 20 |
Z.ai: GLM 5.1
|
Z.ai | 1,465 | ±5 | 30,726 | 88 |
| 21 |
OpenAI: GPT-5.5
|
OpenAI | 1,465 | ±4 | 47,180 | — |
| 22 |
Z.ai: GLM 5.2
|
Z.ai | 1,464 | ±6 | 18,017 | 91 |
| 23 | Mi Xiaomi: MiMo-V2.5-Pro | Xiaomi | 1,463 | ±4 | 42,195 | — |
| 24 |
claude-opus-4-8-thinking
|
Anthropic | 1,463 | ±5 | 30,901 | — |
| 25 |
Qwen: Qwen3.7 Plus
|
Alibaba | 1,459 | ±6 | 22,271 | — |
| 37 | Az amazon-nova-experimental-chat-26-02-10 | Amazon | 1,458 | ±10 | 3,422 | — |
| 26 |
Anthropic: Claude Sonnet 4.6
|
Anthropic | 1,458 | ±4 | 57,183 | 80 |
| 27 |
Google: Gemini 2.5 Pro
|
1,457 | ±2 | 124,370 | 64 | |
| 40 |
Qwen: Qwen3.6 Max Preview
|
Alibaba | 1,456 | ±8 | 5,188 | 90 |
| 28 |
gpt-5.6-sol-xhigh
|
OpenAI | 1,456 | ±8 | 6,221 | — |
| 29 |
MoonshotAI: Kimi K2.6
|
Moonshot AI | 1,455 | ±5 | 37,686 | 93 |
| 30 |
OpenAI: GPT-5.4
|
OpenAI | 1,453 | ±4 | 62,036 | 90 |
| 32 |
grok-4.20-beta-0309-reasoning
|
xAI | 1,452 | ±4 | 60,330 | — |
| 31 |
xAI: Grok 4.5
|
xAI | 1,452 | ±7 | 7,833 | — |
| 33 |
Anthropic: Claude Opus 4.8
|
Anthropic | 1,452 | ±5 | 31,619 | — |
| 34 |
grok-4.20-multi-agent-beta-0309
|
xAI | 1,451 | ±4 | 59,116 | — |
| 35 |
claude-opus-4-5-20251101
|
Anthropic | 1,450 | ±3 | 70,976 | 72 |
| 36 |
DeepSeek: DeepSeek V4 Pro
|
DeepSeek | 1,449 | ±4 | 45,278 | 93 |
| 38 |
dola-seed-2.0-pro
|
ByteDance | 1,448 | ±4 | 67,993 | — |
| 39 |
claude-opus-4-5-20251101-thinking-32k
|
Anthropic | 1,447 | ±4 | 37,037 | — |
| 41 |
deepseek-v4-pro-thinking
|
DeepSeek | 1,445 | ±4 | 43,079 | — |
| 42 |
Z.ai: GLM 5
|
Z.ai | 1,445 | ±4 | 27,785 | 77 |
| 43 |
ernie-5.0-0110
|
Baidu | 1,445 | ±4 | 35,222 | — |
| 44 |
kimi-k2.5-thinking
|
Moonshot AI | 1,445 | ±4 | 62,688 | — |
| 45 |
grok-4.20-beta1
|
xAI | 1,444 | ±5 | 26,822 | — |
| 46 |
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
|
NVIDIA | 1,444 | ±7 | 10,562 | — |
| 47 | TM Thinking Machines: Inkling | Thinking Machines | 1,444 | ±8 | 5,386 | — |
| 48 |
gemini-3-flash
|
1,443 | ±3 | 84,397 | — | |
| 49 |
ernie-5.0-preview-1203
|
Baidu | 1,442 | ±6 | 9,732 | — |
| 50 |
claude-sonnet-5-high
|
Anthropic | 1,441 | ±6 | 13,521 | — |
| 51 |
Google: Gemma 4 31B
|
1,441 | ±8 | 5,880 | — | |
| 52 |
gpt-5.1-high
|
OpenAI | 1,441 | ±4 | 40,774 | — |
| 53 |
Z.ai: GLM 4.6
|
Z.ai | 1,440 | ±4 | 35,608 | — |
| 54 |
Z.ai: GLM 5V Turbo
|
Z.ai | 1,440 | ±7 | 7,558 | — |
| 55 |
qwen3-max-preview
|
Alibaba | 1,439 | ±4 | 27,702 | — |
| 56 |
Qwen: Qwen3.5 397B A17B
|
Alibaba | 1,438 | ±4 | 58,157 | — |
| 57 |
gpt-5.2-chat-latest-20260210
|
OpenAI | 1,438 | ±4 | 34,420 | — |
| 58 |
Google: Gemini 3.5 Flash Lite
|
1,438 | ±9 | 4,674 | — | |
| 59 |
claude-sonnet-4-5-20250929
|
Anthropic | 1,438 | ±3 | 80,720 | 59 |
| 60 |
grok-4.1-thinking
|
xAI | 1,438 | ±3 | 65,461 | — |
| 61 |
Qwen: Qwen3.6 Plus
|
Alibaba | 1,437 | ±4 | 43,912 | 78 |
| 62 |
grok-4.1
|
xAI | 1,437 | ±3 | 67,589 | — |
| 63 | Mi mimo-v2-pro | Xiaomi | 1,436 | ±5 | 24,472 | — |
| 64 |
Z.ai: GLM 4.7
|
Z.ai | 1,436 | ±6 | 12,092 | 68 |
| 65 |
MiniMax: MiniMax M3
|
MiniMax | 1,436 | ±5 | 28,093 | — |
| 66 |
Google: Gemma 4 26B A4B
|
1,434 | ±8 | 5,798 | — | |
| 67 |
claude-sonnet-4-5-20250929-thinking-32k
|
Anthropic | 1,433 | ±3 | 82,316 | — |
| 68 |
DeepSeek: DeepSeek V4 Flash
|
DeepSeek | 1,431 | ±4 | 45,050 | — |
| 69 |
mistral-large-3
|
Mistral | 1,430 | ±3 | 50,849 | — |
| 70 |
ernie-5.0-preview-1022
|
Baidu | 1,430 | ±9 | 4,702 | — |
| 71 |
Z.ai: GLM 4.5
|
Z.ai | 1,429 | ±5 | 24,286 | — |
| 72 |
chatgpt-4o-latest-20250326
|
OpenAI | 1,429 | ±3 | 82,395 | — |
| 73 |
deepseek-r1-0528
|
DeepSeek | 1,428 | ±6 | 18,451 | — |
| 73 |
DeepSeek: R1 0528
|
DeepSeek | 1,428 | ±6 | 18,451 | — |
| 74 | Mi Xiaomi: MiMo-V2.5 | Xiaomi | 1,426 | ±4 | 43,091 | — |
| 75 | Me longcat-flash-chat-2602-exp | meituan | 1,426 | ±5 | 28,070 | — |
| 76 |
mistral-medium-2508
|
Mistral | 1,425 | ±3 | 93,819 | — |
| 77 |
grok-3-preview-02-24
|
xAI | 1,425 | ±4 | 32,894 | — |
| 78 |
deepseek-v4-flash-thinking
|
DeepSeek | 1,424 | ±4 | 44,822 | — |
| 79 |
DeepSeek: DeepSeek V3.2
|
DeepSeek | 1,424 | ±4 | 47,206 | — |
| 80 |
deepseek-v3.2-exp-thinking
|
DeepSeek | 1,424 | ±7 | 9,069 | — |
| 81 |
DeepSeek: DeepSeek V3.2 Exp
|
DeepSeek | 1,423 | ±6 | 11,913 | — |
| 82 | Me longcat-flash-chat | meituan | 1,422 | ±6 | 11,387 | — |
| 83 |
OpenAI: GPT-5.1
|
OpenAI | 1,422 | ±4 | 43,391 | 74 |
| 84 | Mi mimo-v2-omni | Xiaomi | 1,422 | ±6 | 19,461 | — |
| 107 |
IBM: Granite 4.1 8B
|
IBM | 1,422 | ±27 | 4,062 | — |
| 85 |
Qwen: Qwen3 VL 235B A22B Instruct
|
Alibaba | 1,421 | ±6 | 11,499 | — |
| 86 |
Mistral: Mistral Medium 3.5
|
Mistral | 1,421 | ±7 | 11,019 | — |
| 87 |
kimi-k2.5-instant
|
Moonshot AI | 1,421 | ±7 | 8,178 | — |
| 88 |
deepseek-v3.2-thinking
|
DeepSeek | 1,420 | ±4 | 41,025 | — |
| 89 | Az amazon-nova-experimental-chat-12-10 | Amazon | 1,420 | ±10 | 3,676 | — |
| 90 |
deepseek-v3.1-terminus-thinking
|
DeepSeek | 1,420 | ±10 | 3,457 | — |
| 92 |
DeepSeek: DeepSeek V3.1
|
DeepSeek | 1,419 | ±6 | 14,943 | — |
| 93 |
Qwen: Qwen3 235B A22B Instruct 2507
|
Alibaba | 1,419 | ±3 | 97,085 | — |
| 94 |
Qwen: Qwen3 Next 80B A3B Instruct
|
Alibaba | 1,419 | ±5 | 22,859 | — |
| 95 |
claude-opus-4-1-20250805-thinking-16k
|
Anthropic | 1,418 | ±3 | 49,754 | — |
| 96 |
Qwen: Qwen3.5-122B-A10B
|
Alibaba | 1,418 | ±4 | 28,504 | — |
| 97 |
gpt-4.5-preview-2025-02-27
|
OpenAI | 1,417 | ±6 | 14,547 | — |
| 98 |
claude-opus-4-1-20250805
|
Anthropic | 1,417 | ±3 | 77,237 | 49 |
| 100 |
Google: Gemini 2.5 Flash
|
1,417 | ±2 | 124,325 | — | |
| 99 |
DeepSeek: DeepSeek V3.1 Terminus
|
DeepSeek | 1,417 | ±10 | 3,692 | — |
| 101 |
deepseek-v3.1-thinking
|
DeepSeek | 1,417 | ±7 | 11,726 | — |
| 102 | Az amazon-nova-experimental-chat-11-10 | Amazon | 1,416 | ±4 | 25,326 | — |
| 103 |
gpt-5.2-high
|
OpenAI | 1,416 | ±4 | 47,943 | — |
| 104 |
Google: Gemini 3.1 Flash Lite Preview
|
1,415 | ±4 | 60,791 | — | |
| 105 |
kimi-k2-thinking-turbo
|
Moonshot AI | 1,414 | ±3 | 61,950 | — |
| 106 |
Qwen: Qwen3 235B A22B Thinking 2507
|
Alibaba | 1,414 | ±6 | 8,985 | — |
| 107 |
qwen3-max-2025-09-23
|
Alibaba | 1,413 | ±6 | 9,149 | — |
| 108 |
gpt-5.4-mini-high
|
OpenAI | 1,413 | ±4 | 57,822 | — |
| 109 | Mi mimo-v2-flash (non-thinking) | Xiaomi | 1,411 | ±4 | 46,549 | — |
| 109 | Mi mimo-v2-flash (non-thinking) | Xiaomi | 1,411 | ±4 | 46,549 | — |
| 110 |
OpenAI: GPT-5.2
|
OpenAI | 1,411 | ±3 | 77,656 | 80 |
| 111 |
grok-4-0709
|
xAI | 1,410 | ±4 | 41,347 | 67 |
| 112 |
o3-2025-04-16
|
OpenAI | 1,409 | ±4 | 59,699 | — |
| 113 |
grok-4-fast-chat
|
xAI | 1,409 | ±8 | 6,806 | — |
| 114 |
Qwen: Qwen3.5-27B
|
Alibaba | 1,409 | ±4 | 27,314 | — |
| 115 |
grok-4-1-fast-reasoning
|
xAI | 1,408 | ±3 | 56,747 | — |
| 111 | Az amazon-nova-experimental-chat-26-01-10 | Amazon | 1,408 | ±10 | 3,405 | — |
| 116 |
gemini-2.5-flash-preview-09-2025
|
1,407 | ±4 | 32,883 | — | |
| 117 |
hunyuan-vision-1.5-thinking
|
Tencent | 1,406 | ±12 | 2,217 | — |
| 118 |
gpt-5-high
|
OpenAI | 1,405 | ±4 | 31,898 | — |
| 119 |
MiniMax: MiniMax M2.7
|
MiniMax | 1,405 | ±4 | 49,930 | — |
| 120 |
hunyuan-hy3-preview
|
Tencent | 1,404 | ±8 | 6,634 | — |
| 121 | St StepFun: Step 3.5 Flash | stepfun | 1,404 | ±4 | 55,991 | — |
| 122 |
OpenAI: GPT-5 Chat
|
OpenAI | 1,404 | ±4 | 31,536 | — |
| 123 |
Qwen: Qwen3 VL 235B A22B Thinking
|
Alibaba | 1,401 | ±7 | 7,941 | — |
| 124 |
hunyuan-t1-20250711
|
Tencent | 1,400 | ±9 | 4,697 | — |
| 125 |
xAI: Grok 4.3
|
xAI | 1,399 | ±4 | 46,389 | — |
| 127 |
grok-4-fast-reasoning
|
xAI | 1,398 | ±5 | 18,709 | — |
| 128 |
Qwen: Qwen3.5-Flash
|
Alibaba | 1,398 | ±4 | 56,684 | — |
| 129 |
Qwen: Qwen3.5-35B-A3B
|
Alibaba | 1,396 | ±4 | 29,158 | — |
| 130 | Mi mimo-v2-flash (thinking) | Xiaomi | 1,395 | ±6 | 10,934 | — |
| 130 | Mi mimo-v2-flash (thinking) | Xiaomi | 1,395 | ±6 | 10,934 | — |
| 131 | Az amazon-nova-experimental-chat-10-20 | Amazon | 1,394 | ±6 | 11,456 | — |
| 132 |
qwen3-235b-a22b-no-thinking
|
Alibaba | 1,394 | ±4 | 38,174 | — |
| 133 |
claude-haiku-4-5-20251001
|
Anthropic | 1,393 | ±3 | 108,518 | 56 |
| 134 |
minimax-m2.1-preview
|
MiniMax | 1,391 | ±5 | 17,083 | — |
| 135 |
gpt-5.3-chat-latest
|
OpenAI | 1,388 | ±4 | 32,980 | — |
| 136 |
Qwen: Qwen3 30B A3B Instruct 2507
|
Alibaba | 1,384 | ±5 | 23,718 | — |
| 137 |
Z.ai: GLM 4.5 Air
|
Z.ai | 1,383 | ±4 | 31,062 | — |
| 138 |
gpt-4.1-2025-04-14
|
OpenAI | 1,382 | ±4 | 50,935 | — |
| 139 |
kimi-k2-0905-preview
|
Moonshot AI | 1,379 | ±6 | 11,770 | — |
| 140 |
gemini-2.5-flash-lite-preview-09-2025-no-thinking
|
1,379 | ±3 | 47,181 | — | |
| 141 |
nvidia-nemotron-3-super-120b-a12b
|
NVIDIA | 1,379 | ±7 | 7,544 | — |
| 142 |
hunyuan-turbos-20250416
|
Tencent | 1,376 | ±6 | 10,726 | — |
| 143 |
claude-opus-4-20250514-thinking-16k
|
Anthropic | 1,375 | ±4 | 36,861 | — |
| 144 |
DeepSeek: DeepSeek V3 0324
|
DeepSeek | 1,375 | ±4 | 45,480 | 60 |
| 145 |
Z.ai: GLM 4.6V
|
Z.ai | 1,375 | ±11 | 2,797 | — |
| 146 |
gpt-5.4-nano-high
|
OpenAI | 1,374 | ±4 | 56,761 | — |
| 147 |
gpt-5-mini-high
|
OpenAI | 1,374 | ±5 | 27,004 | — |
| 148 |
DeepSeek: R1
|
DeepSeek | 1,373 | ±5 | 18,524 | 68 |
| 148 |
deepseek-r1
|
DeepSeek | 1,373 | ±5 | 18,524 | 68 |
| 149 |
kimi-k2-0711-preview
|
Moonshot AI | 1,371 | ±5 | 27,608 | — |
| 150 |
mistral-medium-2505
|
Mistral | 1,369 | ±5 | 33,193 | — |
| 151 |
gemini-2.5-flash-lite-preview-06-17-thinking
|
1,368 | ±4 | 32,872 | — | |
| 152 |
Qwen: Qwen3 Next 80B A3B Thinking
|
Alibaba | 1,368 | ±6 | 13,678 | — |
| 153 |
grok-3-mini-high
|
xAI | 1,367 | ±5 | 16,951 | — |
| 154 |
qwen2.5-max
|
Alibaba | 1,367 | ±4 | 32,611 | — |
| 155 |
o1-2024-12-17
|
OpenAI | 1,366 | ±4 | 27,807 | — |
| 156 |
Qwen: Qwen3 235B A22B
|
Alibaba | 1,366 | ±5 | 26,254 | — |
| 157 |
OpenAI: gpt-oss-120b
|
OpenAI | 1,366 | ±4 | 30,615 | 61 |
| 158 | Az amazon-nova-experimental-chat-10-09 | Amazon | 1,364 | ±11 | 2,824 | — |
| 159 |
claude-opus-4-20250514
|
Anthropic | 1,364 | ±4 | 44,176 | 62 |
| 160 | AG ling-flash-2.0 | ant-group | 1,363 | ±7 | 6,997 | — |
| 161 |
grok-3-mini-beta
|
xAI | 1,363 | ±5 | 22,688 | — |
| 162 | Az Amazon: Nova 2 Lite | Amazon | 1,363 | ±6 | 12,210 | — |
| 163 |
MiniMax: MiniMax M2.5
|
MiniMax | 1,359 | ±4 | 41,088 | — |
| 164 |
gemma-3-27b-it
|
1,358 | ±4 | 47,508 | 37 | |
| 165 | In Inception: Mercury 2 | inception | 1,357 | ±10 | 3,119 | — |
| 166 |
Qwen3-Coder-480B-A35B-Instruct
|
Alibaba | 1,356 | ±5 | 25,694 | — |
| 167 | I3 intellect-3 | Unknown | 1,356 | ±8 | 5,328 | — |
| 168 | GD gemini-2.0-flash-001 | Google DeepMind,Google | 1,354 | ±4 | 43,737 | 53 |
| 169 |
Z.ai: GLM 4.7 Flash
|
Z.ai | 1,354 | ±6 | 11,719 | — |
| 170 |
o1-preview
|
OpenAI | 1,353 | ±5 | 31,122 | — |
| 171 |
o4-mini-2025-04-16
|
OpenAI | 1,353 | ±4 | 45,415 | — |
| 172 | St step-3 | stepfun | 1,350 | ±7 | 6,532 | — |
| 173 |
nvidia-nemotron-3-nano-30b-a3b-bf16
|
NVIDIA | 1,349 | ±5 | 15,494 | — |
| 174 |
claude-sonnet-4-20250514-thinking-32k
|
Anthropic | 1,348 | ±4 | 35,078 | — |
| 175 |
MiniMax: MiniMax M1
|
MiniMax | 1,342 | ±4 | 35,163 | — |
| 176 |
MiniMax: MiniMax M2
|
MiniMax | 1,342 | ±8 | 6,862 | — |
| 177 | AA Arcee AI: Trinity Large Thinking | arcee-ai | 1,342 | ±5 | 29,139 | — |
| 178 |
gpt-4.1-mini-2025-04-14
|
OpenAI | 1,341 | ±4 | 39,301 | — |
| 179 |
Qwen: Qwen3 32B
|
Alibaba | 1,340 | ±9 | 3,926 | — |
| 180 |
mistral-small-2506
|
Mistral | 1,339 | ±5 | 17,698 | — |
| 181 | TL trinity-large-preview | Unknown | 1,339 | ±4 | 30,052 | — |
| 182 |
claude-sonnet-4-20250514
|
Anthropic | 1,338 | ±4 | 40,277 | — |
| 183 |
nvidia-llama-3.3-nemotron-super-49b-v1.5
|
NVIDIA | 1,338 | ±10 | 3,344 | — |
| 184 |
OpenAI: o3 Mini High
|
OpenAI | 1,337 | ±5 | 18,589 | — |
| 185 | St step-1o-turbo-202506 | stepfun | 1,335 | ±7 | 9,029 | — |
| 186 |
gemma-3-12b-it
|
1,334 | ±9 | 3,829 | — | |
| 187 |
Z.ai: GLM 4.5V
|
Z.ai | 1,334 | ±8 | 4,957 | — |
| 188 |
DeepSeek: DeepSeek V3
|
DeepSeek | 1,333 | ±5 | 21,770 | 44 |
| 189 | AG ring-flash-2.0 | ant-group | 1,332 | ±7 | 7,138 | — |
| 190 |
command-a-03-2025
|
Cohere | 1,331 | ±3 | 56,217 | — |
| 191 |
glm-4-plus-0111
|
Z.ai | 1,331 | ±8 | 5,760 | — |
| 192 |
gemini-2.0-flash-lite-preview-02-05
|
1,330 | ±4 | 24,955 | — | |
| 193 |
QwQ-32B
|
Alibaba | 1,329 | ±4 | 25,379 | — |
| 194 |
qwen-plus-0125
|
Alibaba | 1,327 | ±8 | 5,819 | — |
| 195 | St step-2-16k-exp-202412 | stepfun | 1,321 | ±9 | 4,833 | — |
| 196 |
gpt-5-nano-high
|
OpenAI | 1,320 | ±7 | 8,260 | — |
| 197 |
hunyuan-turbos-20250226
|
Tencent | 1,320 | ±12 | 2,220 | — |
| 198 |
llama-3.1-nemotron-ultra-253b-v1
|
NVIDIA | 1,320 | ±12 | 2,549 | — |
| 199 |
gemini-1.5-pro-002
|
1,319 | ±3 | 55,606 | — | |
| 200 |
OpenAI: o3 Mini
|
OpenAI | 1,319 | ±4 | 57,316 | 82 |
| 201 |
o1-mini
|
OpenAI | 1,317 | ±4 | 51,981 | 56 |
| 202 |
Qwen: Qwen3 30B A3B
|
Alibaba | 1,317 | ±5 | 26,470 | — |
| 203 |
claude-3-7-sonnet-20250219-thinking-32k
|
Anthropic | 1,314 | ±4 | 38,812 | — |
| 204 | A2 olmo-3.1-32b-instruct | Allen Institute for AI | 1,312 | ±6 | 12,211 | — |
| 205 |
hunyuan-turbo-0110
|
Tencent | 1,312 | ±11 | 2,290 | — |
| 206 |
llama-3.3-nemotron-49b-super-v1
|
NVIDIA | 1,308 | ±12 | 2,218 | — |
| 207 |
gemma-3n-e4b-it
|
1,306 | ±5 | 22,565 | — | |
| 208 |
grok-2-2024-08-13
|
xAI | 1,305 | ±4 | 63,498 | — |
| 209 | YL yi-lightning | Unknown | 1,302 | ±5 | 27,332 | — |
| 210 |
gpt-4o-2024-05-13
|
OpenAI | 1,301 | ±3 | 112,881 | — |
| 211 |
claude-3-7-sonnet-20250219
|
Anthropic | 1,299 | ±4 | 43,156 | 70 |
| 212 |
qwen2.5-plus-1127
|
Alibaba | 1,299 | ±6 | 10,187 | — |
| 213 | A2 AllenAI: Olmo 3 32B Think | Allen Institute for AI | 1,299 | ±8 | 5,933 | — |
| 214 |
claude-3-5-sonnet-20241022
|
Anthropic | 1,298 | ±3 | 88,324 | 40 |
| 215 | A2 molmo-2-8b | Allen Institute for AI | 1,294 | ±21 | 799 | — |
| 216 |
deepseek-v2.5-1210
|
DeepSeek | 1,294 | ±8 | 6,795 | — |
| 218 | AV athene-v2-chat | Unknown | 1,292 | ±5 | 24,739 | — |
| 219 |
gemma-3-4b-it
|
1,291 | ±9 | 4,171 | — | |
| 220 |
glm-4-plus
|
Z.ai | 1,290 | ±5 | 26,126 | — |
| 221 |
hunyuan-large-2025-02-10
|
Tencent | 1,288 | ±10 | 3,738 | — |
| 222 |
llama-4-maverick-17b-128e-instruct
|
Meta | 1,288 | ±4 | 39,950 | — |
| 223 |
OpenAI: gpt-oss-20b
|
OpenAI | 1,288 | ±6 | 10,621 | — |
| 224 |
gemini-1.5-flash-002
|
1,287 | ±4 | 34,902 | — | |
| 225 |
gpt-4o-mini-2024-07-18
|
OpenAI | 1,287 | ±4 | 68,709 | — |
| 226 |
gpt-4.1-nano-2025-04-14
|
OpenAI | 1,285 | ±8 | 6,103 | — |
| 227 |
llama-3.1-405b-instruct-bf16
|
Meta | 1,284 | ±4 | 41,375 | — |
| 228 |
llama-3.1-nemotron-70b-instruct
|
NVIDIA | 1,283 | ±8 | 7,140 | — |
| 229 |
gpt-4o-2024-08-06
|
OpenAI | 1,283 | ±4 | 45,499 | — |
| 230 | IA mercury | inception-ai | 1,282 | ±14 | 1,952 | — |
| 231 |
qwen-max-0919
|
Alibaba | 1,282 | ±6 | 16,478 | — |
| 232 |
llama-3.1-405b-instruct-fp8
|
Meta | 1,282 | ±4 | 59,656 | — |
| 233 |
claude-3-5-sonnet-20240620
|
Anthropic | 1,281 | ±3 | 82,419 | — |
| 234 |
grok-2-mini-2024-08-13
|
xAI | 1,281 | ±4 | 52,567 | — |
| 235 |
Llama-4-Scout-17B-16E-Instruct
|
Meta | 1,281 | ±5 | 30,265 | — |
| 236 |
gemini-advanced-0514
|
1,279 | ±5 | 50,148 | — | |
| 237 |
mistral-small-3.1-24b-instruct-2503
|
Mistral | 1,278 | ±4 | 33,189 | — |
| 238 |
Meta: Llama 3.3 70B Instruct
|
Meta | 1,275 | ±3 | 54,723 | 31 |
| 239 |
hunyuan-standard-2025-02-10
|
Tencent | 1,274 | ±10 | 3,904 | — |
| 240 |
gemini-1.5-pro-001
|
1,274 | ±4 | 79,138 | — | |
| 241 |
gpt-4-turbo-2024-04-09
|
OpenAI | 1,272 | ±4 | 98,114 | — |
| 242 |
deepseek-v2.5
|
DeepSeek | 1,271 | ±5 | 24,572 | — |
| 243 | A2 olmo-3.1-32b-think | Allen Institute for AI | 1,270 | ±7 | 8,495 | — |
| 244 |
Qwen2.5 72B Instruct
|
Alibaba | 1,269 | ±4 | 39,406 | — |
| 245 |
Mistral Large 2407
|
Mistral | 1,266 | ±4 | 45,459 | — |
| 246 |
mistral-large-2411
|
Mistral | 1,265 | ±4 | 28,073 | 33 |
| 247 | A7 athene-70b-0725 | Unknown | 1,265 | ±6 | 19,621 | — |
| 248 |
gpt-4-1106-preview
|
OpenAI | 1,264 | ±4 | 100,105 | — |
| 249 |
hunyuan-large-vision
|
Tencent | 1,263 | ±9 | 5,371 | — |
| 250 |
gpt-4-0125-preview
|
OpenAI | 1,262 | ±4 | 93,439 | — |
| 251 |
claude-3-opus-20240229
|
Anthropic | 1,262 | ±3 | 194,909 | 30 |
| 252 |
Meta: Llama 3.1 70B Instruct
|
Meta | 1,261 | ±4 | 55,240 | — |
| 253 | Az amazon.nova-pro-v1:0 | Amazon | 1,259 | ±5 | 24,745 | — |
| 254 | A2 llama-3.1-tulu-3-70b | Allen Institute for AI | 1,256 | ±10 | 2,846 | — |
| 255 |
claude-3-5-haiku-20241022
|
Anthropic | 1,255 | ±3 | 69,935 | 23 |
| 256 |
magistral-medium-2506
|
Mistral | 1,255 | ±6 | 11,625 | — |
| 257 | Re reka-core-20240904 | Reka AI | 1,249 | ±7 | 7,312 | — |
| 258 |
ibm-granite-h-small
|
IBM | 1,242 | ±8 | 5,682 | — |
| 259 |
gemini-1.5-flash-001
|
1,239 | ±4 | 62,833 | — | |
| 260 | J1 jamba-1.5-large | Unknown | 1,237 | ±7 | 8,662 | — |
| 261 |
mistral-small-24b-instruct-2501
|
Mistral | 1,234 | ±6 | 14,681 | — |
| 262 |
gemma-2-27b-it
|
1,232 | ±3 | 75,754 | 19 | |
| 263 |
Qwen2.5 Coder 32B Instruct
|
Alibaba | 1,230 | ±8 | 5,432 | — |
| 264 |
command-r-plus-08-2024
|
Cohere | 1,229 | ±7 | 9,866 | — |
| 265 | Az amazon.nova-lite-v1:0 | Amazon | 1,229 | ±5 | 19,372 | — |
| 266 |
llama-3.1-nemotron-51b-instruct
|
NVIDIA | 1,228 | ±10 | 3,749 | — |
| 267 |
gemma-2-9b-it-simpo
|
1,227 | ±7 | 10,072 | — | |
| 268 |
glm-4-0520
|
Z.ai | 1,226 | ±7 | 9,788 | — |
| 269 |
gemini-1.5-flash-8b-001
|
1,226 | ±4 | 35,558 | — | |
| 270 |
nemotron-4-340b-instruct
|
NVIDIA | 1,225 | ±5 | 19,659 | — |
| 271 |
c4ai-aya-expanse-32b
|
Cohere | 1,224 | ±5 | 27,124 | — |
| 272 |
llama-3-70b-instruct
|
Meta | 1,221 | ±4 | 156,876 | — |
| 273 |
claude-3-sonnet-20240229
|
Anthropic | 1,218 | ±4 | 109,284 | — |
| 274 | Re reka-flash-20240904 | Reka AI | 1,218 | ±7 | 7,536 | — |
| 275 | A2 olmo-2-0325-32b-instruct | Allen Institute for AI | 1,218 | ±11 | 3,334 | — |
| 276 |
Microsoft: Phi 4
|
Microsoft | 1,217 | ±5 | 24,126 | 33 |
| 277 | Az amazon.nova-micro-v1:0 | Amazon | 1,209 | ±5 | 19,364 | — |
| 278 |
gemma-2-9b-it
|
1,208 | ±4 | 54,611 | 10 | |
| 279 |
gpt-4-0314
|
OpenAI | 1,206 | ±5 | 54,173 | — |
| 280 |
command-r-plus
|
Cohere | 1,204 | ±4 | 77,554 | — |
| 281 |
qwen2-72b-instruct
|
Alibaba | 1,203 | ±5 | 37,325 | — |
| 282 |
hunyuan-standard-256k
|
Tencent | 1,202 | ±12 | 2,728 | — |
| 283 |
claude-3-haiku-20240307
|
Anthropic | 1,195 | ±4 | 117,701 | — |
| 284 | A2 llama-3.1-tulu-3-8b | Allen Institute for AI | 1,193 | ±11 | 2,896 | — |
| 285 |
deepseek-coder-v2
|
DeepSeek | 1,191 | ±6 | 15,147 | — |
| 286 |
ministral-8b-2410
|
Mistral | 1,191 | ±9 | 4,781 | — |
| 287 |
command-r-08-2024
|
Cohere | 1,188 | ±7 | 10,140 | — |
| 288 | J1 jamba-1.5-mini | Unknown | 1,187 | ±7 | 8,858 | — |
| 289 |
Meta: Llama 3.1 8B Instruct
|
Meta | 1,187 | ±4 | 49,605 | — |
| 290 |
gpt-4-0613
|
OpenAI | 1,186 | ±4 | 88,723 | — |
| 291 |
c4ai-aya-expanse-8b
|
Cohere | 1,185 | ±7 | 9,818 | — |
| 292 |
mistral-large-2402
|
Mistral | 1,177 | ±5 | 62,436 | — |
| 293 |
qwen1.5-110b-chat
|
Alibaba | 1,175 | ±6 | 26,195 | — |
| 294 | 0A Yi-1.5-34B-Chat | 01.AI | 1,173 | ±5 | 24,146 | — |
| 295 | Re reka-flash-21b-20240226-online | Reka AI | 1,171 | ±7 | 15,450 | — |
| 296 |
qwen1.5-72b-chat
|
Alibaba | 1,166 | ±5 | 39,302 | — |
| 297 |
llama-3-8b-instruct
|
Meta | 1,166 | ±4 | 104,642 | — |
| 298 |
mistral-medium
|
Mistral | 1,165 | ±5 | 34,550 | — |
| 299 | Re reka-flash-21b-20240226 | Reka AI | 1,165 | ±6 | 24,806 | — |
| 300 |
Cohere: Command R (08-2024)
|
Cohere | 1,163 | ±5 | 54,036 | — |
| 301 |
mixtral-8x22b-instruct-v0.1
|
Mistral | 1,162 | ±5 | 51,416 | — |
| 302 |
QwQ-32B-Preview
|
Alibaba | 1,162 | ±11 | 3,231 | — |
| 303 | I5 internlm2_5-20b-chat | Unknown | 1,159 | ±7 | 9,901 | — |
| 304 |
gemma-2-2b-it
|
1,156 | ±4 | 46,616 | — | |
| 305 |
granite-3.1-8b-instruct
|
IBM | 1,150 | ±11 | 3,090 | — |
| 306 |
gemini-pro-dev-api
|
1,149 | ±7 | 18,354 | — | |
| 307 | ZO zephyr-orpo-141b-A35b-v0.1 | Unknown | 1,144 | ±11 | 4,652 | — |
| 308 |
phi-3-medium-4k-instruct
|
Microsoft | 1,138 | ±5 | 25,055 | — |
| 309 |
qwen1.5-32b-chat
|
Alibaba | 1,137 | ±6 | 21,741 | — |
| 310 | SL starling-lm-7b-beta | Unknown | 1,132 | ±7 | 16,056 | — |
| 311 |
Mixtral-8x7B-Instruct-v0.1
|
Mistral | 1,132 | ±4 | 73,503 | — |
| 312 |
gemini-pro
|
1,131 | ±11 | 6,390 | — | |
| 313 | 0A Yi-34B-Chat | 01.AI | 1,129 | ±7 | 15,483 | — |
| 314 |
qwen1.5-14b-chat
|
Alibaba | 1,128 | ±7 | 17,839 | — |
| 315 |
granite-3.1-2b-instruct
|
IBM | 1,128 | ±11 | 3,188 | — |
| 316 |
gpt-3.5-turbo-0125
|
OpenAI | 1,125 | ±5 | 66,207 | — |
| 317 | T2 tulu-2-dpo-70b | Unknown | 1,121 | ±10 | 6,535 | — |
| 318 |
wizardlm-70b
|
Microsoft | 1,120 | ±9 | 8,214 | — |
| 319 | DI dbrx-instruct-preview | Unknown | 1,119 | ±6 | 32,191 | — |
| 320 |
llama-2-70b-chat
|
Meta | 1,115 | ±5 | 38,492 | — |
| 321 |
nous-hermes-2-mixtral-8x7b-dpo
|
Nous Research | 1,112 | ±12 | 3,777 | — |
| 322 |
Phi-3-small-8k-instruct
|
Microsoft | 1,110 | ±6 | 17,766 | — |
| 323 |
Meta: Llama 3.2 3B Instruct
|
Meta | 1,110 | ±8 | 7,936 | — |
| 324 | SL starling-lm-7b-alpha | Unknown | 1,108 | ±8 | 10,224 | — |
| 325 | O3 openchat-3.5-0106 | Unknown | 1,107 | ±8 | 12,637 | — |
| 326 | V3 vicuna-33b | Unknown | 1,105 | ±6 | 22,479 | — |
| 327 |
deepseek-llm-67b-chat
|
DeepSeek | 1,105 | ±12 | 4,932 | — |
| 328 |
snowflake-arctic-instruct
|
Snowflake | 1,101 | ±6 | 32,832 | — |
| 329 |
llama2-70b-steerlm-chat
|
NVIDIA | 1,098 | ±12 | 3,585 | — |
| 330 | O3 openchat-3.5 | Unknown | 1,097 | ±10 | 7,968 | — |
| 331 |
granite-3.0-8b-instruct
|
IBM | 1,097 | ±9 | 6,638 | — |
| 332 |
gpt-3.5-turbo-1106
|
OpenAI | 1,094 | ±9 | 16,619 | — |
| 333 |
gemma-1.1-7b-it
|
1,094 | ±6 | 23,893 | — | |
| 334 | O2 openhermes-2.5-mistral-7b | Unknown | 1,093 | ±10 | 5,006 | — |
| 335 |
mistral-7b-instruct-v0.2
|
Mistral | 1,090 | ±7 | 19,402 | — |
| 336 |
llama-2-13b-chat
|
Meta | 1,085 | ±7 | 19,174 | — |
| 337 |
qwen1.5-7b-chat
|
Alibaba | 1,084 | ±10 | 4,737 | — |
| 338 |
solar-10.7b-instruct-v1.0
|
Upstage | 1,083 | ±13 | 4,155 | — |
| 339 | D2 dolphin-2.2.1-mistral-7b | Unknown | 1,081 | ±15 | 1,679 | — |
| 340 |
phi-3-mini-4k-instruct-june-2024
|
Microsoft | 1,080 | ±6 | 12,297 | — |
| 341 |
granite-3.0-2b-instruct
|
IBM | 1,080 | ±8 | 6,837 | — |
| 342 |
wizardlm-13b
|
Microsoft | 1,077 | ±9 | 7,044 | — |
| 343 |
Phi-3-mini-4k-instruct
|
Microsoft | 1,073 | ±6 | 20,118 | — |
| 344 | Z7 zephyr-7b-beta | Unknown | 1,070 | ±9 | 11,118 | — |
| 345 | M3 mpt-30b-chat | Unknown | 1,069 | ±12 | 2,572 | — |
| 346 |
codellama-34b-instruct
|
Meta | 1,066 | ±9 | 7,366 | — |
| 347 | Z7 zephyr-7b-alpha | Unknown | 1,059 | ±16 | 1,785 | — |
| 348 | V1 vicuna-13b | Unknown | 1,058 | ±7 | 19,367 | — |
| 349 |
codellama-70b-instruct
|
Meta | 1,057 | ±18 | 1,143 | — |
| 350 |
gemma-7b-it
|
1,056 | ±10 | 8,925 | — | |
| 351 |
Meta: Llama 3.2 1B Instruct
|
Meta | 1,055 | ±8 | 8,045 | — |
| 352 | F1 falcon-180b-chat | Unknown | 1,054 | ±17 | 1,295 | — |
| 353 |
llama-2-7b-chat
|
Meta | 1,054 | ±7 | 14,148 | — |
| 354 | G3 guanaco-33b | Unknown | 1,054 | ±12 | 2,921 | — |
| 355 |
qwen-14b-chat
|
Alibaba | 1,051 | ±11 | 4,964 | — |
| 356 |
phi-3-mini-128k-instruct
|
Microsoft | 1,051 | ±7 | 20,685 | — |
| 357 | S1 smollm2-1.7b-instruct | Unknown | 1,042 | ±14 | 2,199 | — |
| 358 | SN stripedhyena-nous-7b | Unknown | 1,039 | ±11 | 5,182 | — |
| 359 | A2 olmo-7b-instruct | Allen Institute for AI | 1,032 | ±11 | 6,328 | — |
| 360 | V7 vicuna-7b | Unknown | 1,031 | ±9 | 6,923 | — |
| 361 |
palm-2
|
1,027 | ±9 | 8,554 | — | |
| 362 |
mistral-7b-instruct
|
Mistral | 1,024 | ±9 | 8,977 | — |
| 363 |
gemma-1.1-2b-it
|
1,022 | ±8 | 10,854 | — | |
| 364 |
gemma-2b-it
|
1,002 | ±12 | 4,780 | — | |
| 365 |
qwen1.5-4b-chat
|
Alibaba | 997 | ±9 | 7,597 | — |
| 366 | K1 koala-13b | Unknown | 990 | ±10 | 6,965 | — |
| 367 | C6 chatglm3-6b | Unknown | 972 | ±12 | 4,658 | — |
| 368 | G1 gpt4all-13b-snoozy | Unknown | 956 | ±15 | 1,743 | — |
| 369 | M7 mpt-7b-chat | Unknown | 955 | ±12 | 3,924 | — |
| 370 | R4 RWKV-4-Raven-14B | Unknown | 949 | ±11 | 4,845 | — |
| 371 | C6 chatglm2-6b | Unknown | 939 | ±13 | 2,658 | — |
| 372 | A1 alpaca-13b | Unknown | 933 | ±11 | 5,745 | — |
| 373 |
chatglm-6b
|
Z.ai | 919 | ±12 | 4,914 | — |
| 374 | OP oasst-pythia-12b | Unknown | 916 | ±11 | 6,310 | — |
| 375 | FT fastchat-t5-3b | Unknown | 895 | ±12 | 4,203 | — |
| 376 | ST stablelm-tuned-alpha-7b | Unknown | 867 | ±13 | 3,287 | — |
| 377 | DV dolly-v2-12b | Unknown | 851 | ±13 | 3,412 | — |
| 378 |
llama-13b
|
Meta | 834 | ±16 | 2,391 | — |
The Known Good
Text Arena (style controlled) — full ranking
381 models rated
11,014,768 votes countedRatings captured 25 Jul 2026 Source: Arena
| # | Model | Creator | Elo | 95% CI | Votes | Known Good Index |
|---|---|---|---|---|---|---|
| 1 |
Anthropic: Claude Fable 5
|
Anthropic | 1,507 | ±6 | 14,646 | — |
| 2 |
claude-opus-4-6-thinking
|
Anthropic | 1,505 | ±4 | 63,191 | — |
| 3 |
claude-opus-4-7-thinking
|
Anthropic | 1,502 | ±4 | 50,683 | — |
| 4 |
Anthropic: Claude Opus 4.6
|
Anthropic | 1,498 | ±4 | 67,037 | 88 |
| 5 |
Meta: Muse Spark 1.1
|
Meta | 1,495 | ±7 | 7,927 | — |
| 6 |
Anthropic: Claude Opus 4.7
|
Anthropic | 1,494 | ±4 | 51,788 | 94 |
| 7 |
muse-spark
|
Meta | 1,488 | ±6 | 13,565 | — |
| 8 |
Google: Gemini 3.1 Pro Preview
|
1,486 | ±4 | 84,631 | 96 | |
| 9 |
Gemini 3 Pro
|
1,486 | ±4 | 41,268 | — | |
| 10 |
MoonshotAI: Kimi K3
|
Moonshot AI | 1,486 | ±10 | 3,619 | — |
| 11 |
gpt-5.6-sol-xhigh
|
OpenAI | 1,485 | ±8 | 6,221 | — |
| 12 |
Google: Gemini 3.6 Flash
|
1,485 | ±9 | 4,747 | — | |
| 13 |
claude-opus-4-8-thinking
|
Anthropic | 1,484 | ±5 | 30,901 | — |
| 14 |
gpt-5.5-high
|
OpenAI | 1,482 | ±4 | 45,760 | — |
| 15 |
gpt-5.4-high
|
OpenAI | 1,478 | ±4 | 58,997 | — |
| 16 |
OpenAI: GPT-5.5
|
OpenAI | 1,476 | ±4 | 47,180 | — |
| 17 |
gemini-3.5-flash-high
|
1,476 | ±7 | 10,092 | — | |
| 18 |
gpt-5.2-chat-latest-20260210
|
OpenAI | 1,476 | ±4 | 34,420 | — |
| 19 |
qwen3.7-max-preview
|
Alibaba | 1,475 | ±10 | 3,714 | — |
| 21 |
gemini-3.5-flash-medium
|
1,474 | ±6 | 14,063 | — | |
| 20 |
grok-4.20-beta1
|
xAI | 1,474 | ±5 | 26,822 | — |
| 22 |
Anthropic: Claude Opus 4.8
|
Anthropic | 1,473 | ±5 | 31,619 | — |
| 23 |
gpt-5.5-instant
|
OpenAI | 1,473 | ±5 | 25,995 | — |
| 24 |
grok-4.20-beta-0309-reasoning
|
xAI | 1,473 | ±4 | 60,330 | — |
| 26 |
claude-opus-4-5-20251101-thinking-32k
|
Anthropic | 1,473 | ±4 | 37,037 | — |
| 27 |
Anthropic: Claude Sonnet 4.6
|
Anthropic | 1,473 | ±4 | 57,183 | 80 |
| 28 |
grok-4.20-multi-agent-beta-0309
|
xAI | 1,471 | ±4 | 59,116 | — |
| 29 |
Z.ai: GLM 5.1
|
Z.ai | 1,470 | ±5 | 30,726 | 88 |
| 30 |
Z.ai: GLM 5.2
|
Z.ai | 1,469 | ±6 | 18,017 | 91 |
| 31 |
claude-opus-4-5-20251101
|
Anthropic | 1,469 | ±3 | 70,976 | 72 |
| 32 |
ernie-5.1
|
Baidu | 1,468 | ±5 | 37,418 | — |
| 33 |
xAI: Grok 4.5
|
xAI | 1,468 | ±7 | 7,833 | — |
| 34 | Mi Xiaomi: MiMo-V2.5-Pro | Xiaomi | 1,467 | ±4 | 42,195 | — |
| 35 |
OpenAI: GPT-5.4
|
OpenAI | 1,466 | ±4 | 62,036 | 90 |
| 36 |
grok-4.1-thinking
|
xAI | 1,466 | ±3 | 65,461 | — |
| 37 |
qwen3.5-max-preview
|
Alibaba | 1,465 | ±5 | 21,479 | — |
| 38 |
claude-sonnet-5-high
|
Anthropic | 1,461 | ±6 | 13,521 | — |
| 39 |
MoonshotAI: Kimi K2.6
|
Moonshot AI | 1,461 | ±5 | 37,686 | 93 |
| 40 |
Qwen: Qwen3.6 Max Preview
|
Alibaba | 1,460 | ±8 | 5,188 | 90 |
| 41 |
Qwen: Qwen3.7 Plus
|
Alibaba | 1,460 | ±6 | 22,271 | — |
| 42 |
grok-4.1
|
xAI | 1,459 | ±3 | 67,589 | — |
| 43 |
Google: Gemini 3.5 Flash Lite
|
1,459 | ±9 | 4,674 | — | |
| 44 |
gemini-3-flash
|
1,459 | ±3 | 84,397 | — | |
| 45 |
Z.ai: GLM 5
|
Z.ai | 1,457 | ±4 | 27,785 | 77 |
| 46 |
DeepSeek: DeepSeek V4 Pro
|
DeepSeek | 1,457 | ±4 | 45,278 | 93 |
| 47 |
claude-sonnet-4-5-20250929-thinking-32k
|
Anthropic | 1,456 | ±3 | 82,316 | — |
| 48 |
dola-seed-2.0-pro
|
ByteDance | 1,455 | ±4 | 67,993 | — |
| 49 |
deepseek-v4-pro-thinking
|
DeepSeek | 1,455 | ±4 | 43,079 | — |
| 50 |
claude-sonnet-4-5-20250929
|
Anthropic | 1,455 | ±3 | 80,720 | 59 |
| 51 |
gpt-5.1-high
|
OpenAI | 1,455 | ±4 | 40,774 | — |
| 52 |
Google: Gemma 4 31B
|
1,451 | ±8 | 5,880 | — | |
| 53 |
kimi-k2.5-thinking
|
Moonshot AI | 1,450 | ±4 | 62,688 | — |
| 54 |
gpt-5.4-mini-high
|
OpenAI | 1,449 | ±4 | 57,822 | — |
| 55 |
claude-opus-4-1-20250805-thinking-16k
|
Anthropic | 1,449 | ±3 | 49,754 | — |
| 56 |
ernie-5.0-preview-1203
|
Baidu | 1,449 | ±7 | 9,732 | — |
| 57 |
gpt-5.3-chat-latest
|
OpenAI | 1,449 | ±4 | 32,980 | — |
| 58 | Mi mimo-v2-pro | Xiaomi | 1,448 | ±5 | 24,472 | — |
| 59 |
claude-opus-4-1-20250805
|
Anthropic | 1,447 | ±3 | 77,237 | 49 |
| 60 |
ernie-5.0-0110
|
Baidu | 1,447 | ±4 | 35,222 | — |
| 61 |
Google: Gemini 2.5 Pro
|
1,446 | ±2 | 124,370 | 64 | |
| 62 | TM Thinking Machines: Inkling | Thinking Machines | 1,445 | ±8 | 5,386 | — |
| 63 |
gpt-4.5-preview-2025-02-27
|
OpenAI | 1,445 | ±6 | 14,547 | — |
| 64 |
MiniMax: MiniMax M3
|
MiniMax | 1,444 | ±5 | 28,093 | — |
| 65 |
Qwen: Qwen3.6 Plus
|
Alibaba | 1,444 | ±4 | 43,912 | 78 |
| 66 |
chatgpt-4o-latest-20250326
|
OpenAI | 1,443 | ±3 | 82,395 | — |
| 67 |
Qwen: Qwen3.5 397B A17B
|
Alibaba | 1,442 | ±4 | 58,157 | — |
| 68 |
Z.ai: GLM 4.7
|
Z.ai | 1,442 | ±6 | 12,092 | 68 |
| 69 |
xAI: Grok 4.3
|
xAI | 1,442 | ±4 | 46,389 | — |
| 70 |
deepseek-v4-flash-thinking
|
DeepSeek | 1,439 | ±4 | 44,822 | — |
| 71 |
OpenAI: GPT-5.1
|
OpenAI | 1,439 | ±4 | 43,391 | 74 |
| 72 |
Google: Gemma 4 26B A4B
|
1,438 | ±8 | 5,798 | — | |
| 73 |
gpt-5.2-high
|
OpenAI | 1,437 | ±4 | 47,943 | — |
| 74 |
Z.ai: GLM 5V Turbo
|
Z.ai | 1,437 | ±7 | 7,558 | — |
| 75 | Me longcat-flash-chat-2602-exp | meituan | 1,436 | ±5 | 28,070 | — |
| 76 |
DeepSeek: DeepSeek V4 Flash
|
DeepSeek | 1,436 | ±4 | 45,050 | — |
| 77 |
qwen3-max-preview
|
Alibaba | 1,435 | ±4 | 27,702 | — |
| 78 |
OpenAI: GPT-5.2
|
OpenAI | 1,434 | ±3 | 77,656 | 80 |
| 79 |
gpt-5-high
|
OpenAI | 1,434 | ±5 | 31,898 | — |
| 80 | Mi Xiaomi: MiMo-V2.5 | Xiaomi | 1,433 | ±4 | 43,091 | — |
| 81 |
Google: Gemini 3.1 Flash Lite Preview
|
1,432 | ±4 | 60,791 | — | |
| 82 |
kimi-k2.5-instant
|
Moonshot AI | 1,431 | ±7 | 8,178 | — |
| 83 |
grok-4-1-fast-reasoning
|
xAI | 1,431 | ±3 | 56,747 | — |
| 84 |
o3-2025-04-16
|
OpenAI | 1,431 | ±4 | 59,699 | — |
| 85 | Mi mimo-v2-omni | Xiaomi | 1,430 | ±6 | 19,461 | — |
| 86 |
kimi-k2-thinking-turbo
|
Moonshot AI | 1,430 | ±3 | 61,950 | — |
| 87 |
Mistral: Mistral Medium 3.5
|
Mistral | 1,427 | ±7 | 11,019 | — |
| 88 | Az amazon-nova-experimental-chat-26-02-10 | Amazon | 1,427 | ±10 | 3,422 | — |
| 89 |
OpenAI: GPT-5 Chat
|
OpenAI | 1,427 | ±4 | 31,536 | — |
| 90 |
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
|
NVIDIA | 1,425 | ±7 | 10,562 | — |
| 91 |
Z.ai: GLM 4.6
|
Z.ai | 1,425 | ±4 | 35,608 | — |
| 92 |
DeepSeek: DeepSeek V3.2
|
DeepSeek | 1,425 | ±4 | 47,206 | — |
| 93 |
deepseek-v3.2-exp-thinking
|
DeepSeek | 1,425 | ±7 | 9,069 | — |
| 94 |
claude-opus-4-20250514-thinking-16k
|
Anthropic | 1,424 | ±4 | 36,861 | — |
| 95 |
qwen3-max-2025-09-23
|
Alibaba | 1,424 | ±6 | 9,149 | — |
| 96 |
Qwen: Qwen3 235B A22B Instruct 2507
|
Alibaba | 1,423 | ±3 | 97,085 | — |
| 97 |
deepseek-v3.2-thinking
|
DeepSeek | 1,423 | ±4 | 41,025 | — |
| 98 |
DeepSeek: DeepSeek V3.2 Exp
|
DeepSeek | 1,423 | ±6 | 11,913 | — |
| 99 |
deepseek-r1-0528
|
DeepSeek | 1,422 | ±6 | 18,451 | — |
| 99 |
DeepSeek: R1 0528
|
DeepSeek | 1,422 | ±6 | 18,451 | — |
| 100 |
grok-4-fast-chat
|
xAI | 1,421 | ±8 | 6,806 | — |
| 101 |
ernie-5.0-preview-1022
|
Baidu | 1,419 | ±9 | 4,702 | — |
| 102 |
kimi-k2-0905-preview
|
Moonshot AI | 1,418 | ±6 | 11,770 | — |
| 103 |
DeepSeek: DeepSeek V3.1
|
DeepSeek | 1,417 | ±6 | 14,943 | — |
| 104 |
kimi-k2-0711-preview
|
Moonshot AI | 1,417 | ±5 | 27,608 | — |
| 105 |
Qwen: Qwen3.5-122B-A10B
|
Alibaba | 1,417 | ±4 | 28,504 | — |
| 106 |
deepseek-v3.1-terminus-thinking
|
DeepSeek | 1,417 | ±10 | 3,457 | — |
| 107 |
deepseek-v3.1-thinking
|
DeepSeek | 1,417 | ±7 | 11,726 | — |
| 108 |
MiniMax: MiniMax M2.7
|
MiniMax | 1,417 | ±4 | 49,930 | — |
| 109 | Az amazon-nova-experimental-chat-26-01-10 | Amazon | 1,415 | ±10 | 3,405 | — |
| 110 |
mistral-large-3
|
Mistral | 1,415 | ±3 | 50,849 | — |
| 111 |
DeepSeek: DeepSeek V3.1 Terminus
|
DeepSeek | 1,415 | ±10 | 3,692 | — |
| 112 |
Qwen: Qwen3 VL 235B A22B Instruct
|
Alibaba | 1,415 | ±6 | 11,499 | — |
| 113 |
gpt-4.1-2025-04-14
|
OpenAI | 1,414 | ±4 | 50,935 | — |
| 114 |
claude-opus-4-20250514
|
Anthropic | 1,412 | ±4 | 44,176 | 62 |
| 115 |
claude-haiku-4-5-20251001
|
Anthropic | 1,412 | ±3 | 108,518 | 56 |
| 116 |
hunyuan-hy3-preview
|
Tencent | 1,412 | ±8 | 6,634 | — |
| 117 |
grok-3-preview-02-24
|
xAI | 1,412 | ±4 | 32,894 | — |
| 118 |
Z.ai: GLM 4.5
|
Z.ai | 1,411 | ±5 | 24,286 | — |
| 119 |
Google: Gemini 2.5 Flash
|
1,410 | ±2 | 124,325 | — | |
| 120 |
mistral-medium-2508
|
Mistral | 1,410 | ±3 | 93,819 | — |
| 121 |
grok-4-0709
|
xAI | 1,410 | ±4 | 41,347 | 67 |
| 122 |
Qwen: Qwen3.5-27B
|
Alibaba | 1,409 | ±4 | 27,314 | — |
| 123 |
gemini-2.5-flash-preview-09-2025
|
1,404 | ±4 | 32,883 | — | |
| 124 |
grok-4-fast-reasoning
|
xAI | 1,404 | ±5 | 18,709 | — |
| 125 |
gpt-5.4-nano-high
|
OpenAI | 1,404 | ±4 | 56,761 | — |
| 126 |
qwen3-235b-a22b-no-thinking
|
Alibaba | 1,403 | ±4 | 38,174 | — |
| 127 |
o1-2024-12-17
|
OpenAI | 1,402 | ±4 | 27,807 | — |
| 128 |
Qwen: Qwen3 Next 80B A3B Instruct
|
Alibaba | 1,401 | ±5 | 22,859 | — |
| 129 | Me longcat-flash-chat | meituan | 1,401 | ±6 | 11,387 | — |
| 130 |
claude-sonnet-4-20250514-thinking-32k
|
Anthropic | 1,399 | ±4 | 35,078 | — |
| 131 |
Qwen: Qwen3 235B A22B Thinking 2507
|
Alibaba | 1,399 | ±7 | 8,985 | — |
| 132 |
DeepSeek: R1
|
DeepSeek | 1,398 | ±5 | 18,524 | 68 |
| 132 |
deepseek-r1
|
DeepSeek | 1,398 | ±5 | 18,524 | 68 |
| 133 |
Qwen: Qwen3.5-Flash
|
Alibaba | 1,397 | ±4 | 56,684 | — |
| 134 |
Qwen: Qwen3.5-35B-A3B
|
Alibaba | 1,396 | ±4 | 29,158 | — |
| 135 |
DeepSeek: DeepSeek V3 0324
|
DeepSeek | 1,396 | ±4 | 45,480 | 60 |
| 136 |
Qwen: Qwen3 VL 235B A22B Thinking
|
Alibaba | 1,395 | ±7 | 7,941 | — |
| 137 |
hunyuan-vision-1.5-thinking
|
Tencent | 1,395 | ±12 | 2,217 | — |
| 138 | St StepFun: Step 3.5 Flash | stepfun | 1,395 | ±4 | 55,991 | — |
| 139 | Az amazon-nova-experimental-chat-12-10 | Amazon | 1,394 | ±10 | 3,676 | — |
| 140 | Mi mimo-v2-flash (non-thinking) | Xiaomi | 1,393 | ±4 | 46,549 | — |
| 140 | Mi mimo-v2-flash (non-thinking) | Xiaomi | 1,393 | ±4 | 46,549 | — |
| 141 |
MiniMax: MiniMax M2.5
|
MiniMax | 1,390 | ±4 | 41,088 | — |
| 142 |
gpt-5-mini-high
|
OpenAI | 1,390 | ±5 | 27,004 | — |
| 143 |
o4-mini-2025-04-16
|
OpenAI | 1,390 | ±4 | 45,415 | — |
| 144 |
claude-sonnet-4-20250514
|
Anthropic | 1,389 | ±4 | 40,277 | — |
| 145 |
o1-preview
|
OpenAI | 1,388 | ±5 | 31,122 | — |
| 146 |
Qwen3-Coder-480B-A35B-Instruct
|
Alibaba | 1,388 | ±5 | 25,694 | — |
| 147 |
claude-3-7-sonnet-20250219-thinking-32k
|
Anthropic | 1,387 | ±4 | 38,812 | — |
| 148 | Mi mimo-v2-flash (thinking) | Xiaomi | 1,387 | ±6 | 10,934 | — |
| 148 | Mi mimo-v2-flash (thinking) | Xiaomi | 1,387 | ±6 | 10,934 | — |
| 149 |
mistral-medium-2505
|
Mistral | 1,387 | ±5 | 33,193 | — |
| 150 |
hunyuan-t1-20250711
|
Tencent | 1,387 | ±9 | 4,697 | — |
| 151 |
minimax-m2.1-preview
|
MiniMax | 1,384 | ±5 | 17,083 | — |
| 152 |
Qwen: Qwen3 30B A3B Instruct 2507
|
Alibaba | 1,383 | ±5 | 23,718 | — |
| 153 |
gpt-4.1-mini-2025-04-14
|
OpenAI | 1,383 | ±4 | 39,301 | — |
| 154 |
hunyuan-turbos-20250416
|
Tencent | 1,382 | ±6 | 10,726 | — |
| 155 |
gemini-2.5-flash-lite-preview-09-2025-no-thinking
|
1,380 | ±3 | 47,181 | — | |
| 156 | TL trinity-large-preview | Unknown | 1,378 | ±4 | 30,052 | — |
| 157 |
Z.ai: GLM 4.6V
|
Z.ai | 1,377 | ±11 | 2,797 | — |
| 158 |
Qwen: Qwen3 235B A22B
|
Alibaba | 1,375 | ±5 | 26,254 | — |
| 159 |
gemini-2.5-flash-lite-preview-06-17-thinking
|
1,374 | ±5 | 32,872 | — | |
| 160 |
qwen2.5-max
|
Alibaba | 1,374 | ±4 | 32,611 | — |
| 161 |
claude-3-5-sonnet-20241022
|
Anthropic | 1,373 | ±3 | 88,324 | 40 |
| 162 |
Z.ai: GLM 4.5 Air
|
Z.ai | 1,373 | ±4 | 31,062 | — |
| 163 |
claude-3-7-sonnet-20250219
|
Anthropic | 1,371 | ±4 | 43,156 | 70 |
| 164 |
Qwen: Qwen3 Next 80B A3B Thinking
|
Alibaba | 1,370 | ±6 | 13,678 | — |
| 165 | AA Arcee AI: Trinity Large Thinking | arcee-ai | 1,369 | ±5 | 29,139 | — |
| 166 |
Z.ai: GLM 4.7 Flash
|
Z.ai | 1,368 | ±6 | 11,719 | — |
| 167 | Az amazon-nova-experimental-chat-11-10 | Amazon | 1,366 | ±4 | 25,326 | — |
| 168 |
gemma-3-27b-it
|
1,366 | ±4 | 47,508 | 37 | |
| 169 |
MiniMax: MiniMax M1
|
MiniMax | 1,364 | ±4 | 35,163 | — |
| 170 |
OpenAI: o3 Mini High
|
OpenAI | 1,363 | ±5 | 18,589 | — |
| 171 |
grok-3-mini-high
|
xAI | 1,362 | ±5 | 16,951 | — |
| 172 |
nvidia-nemotron-3-super-120b-a12b
|
NVIDIA | 1,362 | ±7 | 7,544 | — |
| 173 | GD gemini-2.0-flash-001 | Google DeepMind,Google | 1,360 | ±4 | 43,737 | 53 |
| 174 |
DeepSeek: DeepSeek V3
|
DeepSeek | 1,358 | ±5 | 21,770 | 44 |
| 175 |
mistral-small-2506
|
Mistral | 1,358 | ±5 | 17,698 | — |
| 176 |
grok-3-mini-beta
|
xAI | 1,357 | ±5 | 22,688 | — |
| 177 | I3 intellect-3 | Unknown | 1,356 | ±8 | 5,328 | — |
| 178 |
command-a-03-2025
|
Cohere | 1,354 | ±3 | 56,217 | — |
| 179 |
gemini-2.0-flash-lite-preview-02-05
|
1,353 | ±4 | 24,955 | — | |
| 180 |
Z.ai: GLM 4.5V
|
Z.ai | 1,353 | ±8 | 4,957 | — |
| 181 |
OpenAI: gpt-oss-120b
|
OpenAI | 1,352 | ±4 | 30,615 | 61 |
| 182 |
gemini-1.5-pro-002
|
1,351 | ±3 | 55,606 | — | |
| 183 | Az amazon-nova-experimental-chat-10-20 | Amazon | 1,350 | ±6 | 11,456 | — |
| 184 |
hunyuan-turbos-20250226
|
Tencent | 1,349 | ±12 | 2,220 | — |
| 185 | St step-3 | stepfun | 1,348 | ±7 | 6,532 | — |
| 186 |
OpenAI: o3 Mini
|
OpenAI | 1,348 | ±4 | 57,316 | 82 |
| 187 | Az amazon-nova-experimental-chat-10-09 | Amazon | 1,348 | ±11 | 2,824 | — |
| 188 |
llama-3.1-nemotron-ultra-253b-v1
|
NVIDIA | 1,347 | ±12 | 2,549 | — |
| 189 |
Qwen: Qwen3 32B
|
Alibaba | 1,347 | ±9 | 3,926 | — |
| 190 | In Inception: Mercury 2 | inception | 1,347 | ±11 | 3,119 | — |
| 191 | AG ling-flash-2.0 | ant-group | 1,346 | ±7 | 6,997 | — |
| 192 |
qwen-plus-0125
|
Alibaba | 1,346 | ±8 | 5,819 | — |
| 193 |
MiniMax: MiniMax M2
|
MiniMax | 1,346 | ±8 | 6,862 | — |
| 194 |
gpt-4o-2024-05-13
|
OpenAI | 1,346 | ±3 | 112,881 | — |
| 195 |
nvidia-llama-3.3-nemotron-super-49b-v1.5
|
NVIDIA | 1,343 | ±10 | 3,344 | — |
| 196 |
glm-4-plus-0111
|
Z.ai | 1,343 | ±8 | 5,760 | — |
| 197 |
claude-3-5-sonnet-20240620
|
Anthropic | 1,342 | ±3 | 82,419 | — |
| 198 |
gemma-3-12b-it
|
1,342 | ±10 | 3,829 | — | |
| 199 |
hunyuan-turbo-0110
|
Tencent | 1,341 | ±12 | 2,290 | — |
| 200 |
gpt-5-nano-high
|
OpenAI | 1,337 | ±7 | 8,260 | — |
| 201 |
o1-mini
|
OpenAI | 1,337 | ±4 | 51,981 | 56 |
| 202 | Az Amazon: Nova 2 Lite | Amazon | 1,337 | ±6 | 12,210 | — |
| 203 |
QwQ-32B
|
Alibaba | 1,336 | ±4 | 25,379 | — |
| 204 |
grok-2-2024-08-13
|
xAI | 1,336 | ±4 | 63,498 | — |
| 205 |
gemini-advanced-0514
|
1,335 | ±5 | 50,148 | — | |
| 206 |
gpt-4o-2024-08-06
|
OpenAI | 1,335 | ±4 | 45,499 | — |
| 207 |
llama-3.1-405b-instruct-bf16
|
Meta | 1,335 | ±4 | 41,375 | — |
| 208 | St step-2-16k-exp-202412 | stepfun | 1,334 | ±9 | 4,833 | — |
| 209 |
llama-3.1-405b-instruct-fp8
|
Meta | 1,333 | ±4 | 59,656 | — |
| 210 | A2 olmo-3.1-32b-instruct | Allen Institute for AI | 1,330 | ±6 | 12,211 | — |
| 211 | A2 molmo-2-8b | Allen Institute for AI | 1,328 | ±21 | 799 | — |
| 212 | YL yi-lightning | Unknown | 1,328 | ±5 | 27,332 | — |
| 213 |
llama-3.3-nemotron-49b-super-v1
|
NVIDIA | 1,328 | ±12 | 2,218 | — |
| 214 |
Qwen: Qwen3 30B A3B
|
Alibaba | 1,327 | ±5 | 26,470 | — |
| 215 |
llama-4-maverick-17b-128e-instruct
|
Meta | 1,327 | ±4 | 39,950 | — |
| 216 |
hunyuan-large-2025-02-10
|
Tencent | 1,326 | ±10 | 3,738 | — |
| 217 |
gpt-4-turbo-2024-04-09
|
OpenAI | 1,324 | ±4 | 98,114 | — |
| 218 |
claude-3-5-haiku-20241022
|
Anthropic | 1,324 | ±3 | 69,935 | 23 |
| 219 |
gemini-1.5-pro-001
|
1,324 | ±4 | 79,138 | — | |
| 220 |
deepseek-v2.5-1210
|
DeepSeek | 1,323 | ±8 | 6,795 | — |
| 221 |
Llama-4-Scout-17B-16E-Instruct
|
Meta | 1,323 | ±5 | 30,265 | — |
| 222 |
gpt-4.1-nano-2025-04-14
|
OpenAI | 1,322 | ±8 | 6,103 | — |
| 223 |
claude-3-opus-20240229
|
Anthropic | 1,321 | ±3 | 194,909 | 30 |
| 224 | AG ring-flash-2.0 | ant-group | 1,321 | ±7 | 7,138 | — |
| 225 | St step-1o-turbo-202506 | stepfun | 1,320 | ±7 | 9,029 | — |
| 226 |
glm-4-plus
|
Z.ai | 1,319 | ±5 | 26,126 | — |
| 227 |
Meta: Llama 3.3 70B Instruct
|
Meta | 1,318 | ±3 | 54,723 | 31 |
| 228 |
gemma-3n-e4b-it
|
1,318 | ±5 | 22,565 | — | |
| 229 |
qwen-max-0919
|
Alibaba | 1,318 | ±6 | 16,478 | — |
| 230 |
gpt-4o-mini-2024-07-18
|
OpenAI | 1,318 | ±4 | 68,709 | — |
| 231 |
OpenAI: gpt-oss-20b
|
OpenAI | 1,317 | ±6 | 10,621 | — |
| 232 |
nvidia-nemotron-3-nano-30b-a3b-bf16
|
NVIDIA | 1,316 | ±6 | 15,494 | — |
| 233 |
qwen2.5-plus-1127
|
Alibaba | 1,315 | ±6 | 10,187 | — |
| 234 | AV athene-v2-chat | Unknown | 1,314 | ±5 | 24,739 | — |
| 235 |
Mistral Large 2407
|
Mistral | 1,314 | ±4 | 45,459 | — |
| 236 |
gpt-4-0125-preview
|
OpenAI | 1,313 | ±4 | 93,439 | — |
| 237 |
gpt-4-1106-preview
|
OpenAI | 1,312 | ±4 | 100,105 | — |
| 238 |
hunyuan-standard-2025-02-10
|
Tencent | 1,311 | ±10 | 3,904 | — |
| 239 |
gemini-1.5-flash-002
|
1,309 | ±4 | 34,902 | — | |
| 240 |
grok-2-mini-2024-08-13
|
xAI | 1,308 | ±4 | 52,567 | — |
| 241 |
deepseek-v2.5
|
DeepSeek | 1,307 | ±5 | 24,572 | — |
| 242 |
IBM: Granite 4.1 8B
|
IBM | 1,307 | ±10 | 4,062 | — |
| 243 | A7 athene-70b-0725 | Unknown | 1,306 | ±6 | 19,621 | — |
| 244 | IA mercury | inception-ai | 1,306 | ±14 | 1,952 | — |
| 245 | A2 AllenAI: Olmo 3 32B Think | Allen Institute for AI | 1,306 | ±8 | 5,933 | — |
| 246 |
mistral-large-2411
|
Mistral | 1,305 | ±4 | 28,073 | 33 |
| 247 |
magistral-medium-2506
|
Mistral | 1,304 | ±6 | 11,625 | — |
| 248 |
gemma-3-4b-it
|
1,303 | ±9 | 4,171 | — | |
| 249 |
mistral-small-3.1-24b-instruct-2503
|
Mistral | 1,303 | ±5 | 33,189 | — |
| 250 |
Qwen2.5 72B Instruct
|
Alibaba | 1,303 | ±4 | 39,406 | — |
| 251 |
llama-3.1-nemotron-70b-instruct
|
NVIDIA | 1,299 | ±8 | 7,140 | — |
| 252 |
hunyuan-large-vision
|
Tencent | 1,294 | ±9 | 5,371 | — |
| 253 |
Meta: Llama 3.1 70B Instruct
|
Meta | 1,293 | ±4 | 55,240 | — |
| 254 | Az amazon.nova-pro-v1:0 | Amazon | 1,290 | ±5 | 24,745 | — |
| 255 | J1 jamba-1.5-large | Unknown | 1,289 | ±7 | 8,662 | — |
| 256 |
gemma-2-27b-it
|
1,289 | ±3 | 75,754 | 19 | |
| 257 | Re reka-core-20240904 | Reka AI | 1,288 | ±7 | 7,312 | — |
| 258 |
ibm-granite-h-small
|
IBM | 1,287 | ±8 | 5,682 | — |
| 259 |
gpt-4-0314
|
OpenAI | 1,287 | ±5 | 54,173 | — |
| 260 |
gemini-1.5-flash-001
|
1,286 | ±4 | 62,833 | — | |
| 261 |
llama-3.1-nemotron-51b-instruct
|
NVIDIA | 1,286 | ±10 | 3,749 | — |
| 262 | A2 llama-3.1-tulu-3-70b | Allen Institute for AI | 1,286 | ±10 | 2,846 | — |
| 263 | A2 olmo-3.1-32b-think | Allen Institute for AI | 1,285 | ±7 | 8,495 | — |
| 264 |
claude-3-sonnet-20240229
|
Anthropic | 1,281 | ±4 | 109,284 | — |
| 265 |
gemma-2-9b-it-simpo
|
1,280 | ±7 | 10,072 | — | |
| 266 |
nemotron-4-340b-instruct
|
NVIDIA | 1,277 | ±5 | 19,659 | — |
| 267 |
llama-3-70b-instruct
|
Meta | 1,276 | ±4 | 156,876 | — |
| 268 |
command-r-plus-08-2024
|
Cohere | 1,276 | ±7 | 9,866 | — |
| 269 |
gpt-4-0613
|
OpenAI | 1,275 | ±4 | 88,723 | — |
| 270 |
mistral-small-24b-instruct-2501
|
Mistral | 1,274 | ±6 | 14,681 | — |
| 271 |
glm-4-0520
|
Z.ai | 1,273 | ±7 | 9,788 | — |
| 272 | Re reka-flash-20240904 | Reka AI | 1,272 | ±7 | 7,536 | — |
| 273 |
Qwen2.5 Coder 32B Instruct
|
Alibaba | 1,270 | ±8 | 5,432 | — |
| 274 |
c4ai-aya-expanse-32b
|
Cohere | 1,267 | ±5 | 27,124 | — |
| 275 |
gemma-2-9b-it
|
1,266 | ±4 | 54,611 | 10 | |
| 276 |
deepseek-coder-v2
|
DeepSeek | 1,265 | ±6 | 15,147 | — |
| 277 |
qwen2-72b-instruct
|
Alibaba | 1,261 | ±5 | 37,325 | — |
| 278 |
command-r-plus
|
Cohere | 1,261 | ±4 | 77,554 | — |
| 279 |
claude-3-haiku-20240307
|
Anthropic | 1,261 | ±4 | 117,701 | — |
| 280 | Az amazon.nova-lite-v1:0 | Amazon | 1,260 | ±5 | 19,372 | — |
| 281 |
gemini-1.5-flash-8b-001
|
1,259 | ±4 | 35,558 | — | |
| 282 |
Microsoft: Phi 4
|
Microsoft | 1,256 | ±5 | 24,126 | 33 |
| 283 | A2 olmo-2-0325-32b-instruct | Allen Institute for AI | 1,251 | ±11 | 3,334 | — |
| 284 |
command-r-08-2024
|
Cohere | 1,250 | ±7 | 10,140 | — |
| 285 |
mistral-large-2402
|
Mistral | 1,242 | ±5 | 62,436 | — |
| 286 | Az amazon.nova-micro-v1:0 | Amazon | 1,241 | ±5 | 19,364 | — |
| 287 | J1 jamba-1.5-mini | Unknown | 1,239 | ±7 | 8,858 | — |
| 288 |
ministral-8b-2410
|
Mistral | 1,237 | ±9 | 4,781 | — |
| 289 |
gemini-pro-dev-api
|
1,236 | ±7 | 18,354 | — | |
| 290 |
qwen1.5-110b-chat
|
Alibaba | 1,234 | ±6 | 26,195 | — |
| 291 |
hunyuan-standard-256k
|
Tencent | 1,233 | ±12 | 2,728 | — |
| 292 | Re reka-flash-21b-20240226-online | Reka AI | 1,233 | ±7 | 15,450 | — |
| 293 |
qwen1.5-72b-chat
|
Alibaba | 1,233 | ±5 | 39,302 | — |
| 294 |
mixtral-8x22b-instruct-v0.1
|
Mistral | 1,229 | ±5 | 51,416 | — |
| 296 |
Cohere: Command R (08-2024)
|
Cohere | 1,226 | ±5 | 54,036 | — |
| 295 | Re reka-flash-21b-20240226 | Reka AI | 1,226 | ±6 | 24,806 | — |
| 297 |
gpt-3.5-turbo-0125
|
OpenAI | 1,224 | ±5 | 66,207 | — |
| 298 |
llama-3-8b-instruct
|
Meta | 1,223 | ±4 | 104,642 | — |
| 299 |
c4ai-aya-expanse-8b
|
Cohere | 1,223 | ±7 | 9,818 | — |
| 300 |
gemini-pro
|
1,222 | ±12 | 6,390 | — | |
| 301 |
mistral-medium
|
Mistral | 1,222 | ±5 | 34,550 | — |
| 302 | A2 llama-3.1-tulu-3-8b | Allen Institute for AI | 1,220 | ±11 | 2,896 | — |
| 303 | 0A Yi-1.5-34B-Chat | 01.AI | 1,212 | ±5 | 24,146 | — |
| 304 | ZO zephyr-orpo-141b-A35b-v0.1 | Unknown | 1,212 | ±11 | 4,652 | — |
| 305 |
Meta: Llama 3.1 8B Instruct
|
Meta | 1,211 | ±4 | 49,605 | — |
| 306 |
granite-3.1-8b-instruct
|
IBM | 1,208 | ±11 | 3,090 | — |
| 307 |
qwen1.5-32b-chat
|
Alibaba | 1,203 | ±6 | 21,741 | — |
| 308 |
gpt-3.5-turbo-1106
|
OpenAI | 1,203 | ±9 | 16,619 | — |
| 309 |
gemma-2-2b-it
|
1,200 | ±4 | 46,616 | — | |
| 310 |
phi-3-medium-4k-instruct
|
Microsoft | 1,197 | ±5 | 25,055 | — |
| 311 |
Mixtral-8x7B-Instruct-v0.1
|
Mistral | 1,196 | ±4 | 73,503 | — |
| 312 | DI dbrx-instruct-preview | Unknown | 1,195 | ±6 | 32,191 | — |
| 313 | I5 internlm2_5-20b-chat | Unknown | 1,191 | ±7 | 9,901 | — |
| 314 |
qwen1.5-14b-chat
|
Alibaba | 1,190 | ±7 | 17,839 | — |
| 315 |
wizardlm-70b
|
Microsoft | 1,184 | ±9 | 8,214 | — |
| 316 |
deepseek-llm-67b-chat
|
DeepSeek | 1,184 | ±11 | 4,932 | — |
| 317 | 0A Yi-34B-Chat | 01.AI | 1,183 | ±7 | 15,483 | — |
| 318 |
granite-3.0-8b-instruct
|
IBM | 1,182 | ±9 | 6,638 | — |
| 319 | O3 openchat-3.5 | Unknown | 1,182 | ±10 | 7,968 | — |
| 320 | O3 openchat-3.5-0106 | Unknown | 1,182 | ±8 | 12,637 | — |
| 321 |
gemma-1.1-7b-it
|
1,182 | ±6 | 23,893 | — | |
| 322 |
snowflake-arctic-instruct
|
Snowflake | 1,179 | ±6 | 32,832 | — |
| 323 |
granite-3.1-2b-instruct
|
IBM | 1,178 | ±11 | 3,188 | — |
| 324 | T2 tulu-2-dpo-70b | Unknown | 1,177 | ±10 | 6,535 | — |
| 325 | O2 openhermes-2.5-mistral-7b | Unknown | 1,175 | ±10 | 5,006 | — |
| 326 | V3 vicuna-33b | Unknown | 1,172 | ±6 | 22,479 | — |
| 327 | SL starling-lm-7b-beta | Unknown | 1,171 | ±7 | 16,056 | — |
| 328 |
Phi-3-small-8k-instruct
|
Microsoft | 1,170 | ±6 | 17,766 | — |
| 329 |
llama-2-70b-chat
|
Meta | 1,170 | ±6 | 38,492 | — |
| 330 | SL starling-lm-7b-alpha | Unknown | 1,167 | ±8 | 10,224 | — |
| 331 |
Meta: Llama 3.2 3B Instruct
|
Meta | 1,166 | ±8 | 7,936 | — |
| 332 |
nous-hermes-2-mixtral-8x7b-dpo
|
Nous Research | 1,164 | ±12 | 3,777 | — |
| 333 |
granite-3.0-2b-instruct
|
IBM | 1,156 | ±8 | 6,837 | — |
| 334 |
QwQ-32B-Preview
|
Alibaba | 1,155 | ±11 | 3,231 | — |
| 335 |
llama2-70b-steerlm-chat
|
NVIDIA | 1,154 | ±13 | 3,585 | — |
| 336 |
solar-10.7b-instruct-v1.0
|
Upstage | 1,152 | ±13 | 4,155 | — |
| 337 | D2 dolphin-2.2.1-mistral-7b | Unknown | 1,151 | ±15 | 1,679 | — |
| 338 | M3 mpt-30b-chat | Unknown | 1,150 | ±12 | 2,572 | — |
| 339 |
mistral-7b-instruct-v0.2
|
Mistral | 1,149 | ±7 | 19,402 | — |
| 340 |
wizardlm-13b
|
Microsoft | 1,149 | ±9 | 7,044 | — |
| 341 | F1 falcon-180b-chat | Unknown | 1,147 | ±17 | 1,295 | — |
| 342 |
qwen1.5-7b-chat
|
Alibaba | 1,143 | ±10 | 4,737 | — |
| 343 |
phi-3-mini-4k-instruct-june-2024
|
Microsoft | 1,142 | ±6 | 12,297 | — |
| 344 |
llama-2-13b-chat
|
Meta | 1,141 | ±7 | 19,174 | — |
| 345 | V1 vicuna-13b | Unknown | 1,141 | ±7 | 19,367 | — |
| 346 |
qwen-14b-chat
|
Alibaba | 1,138 | ±11 | 4,964 | — |
| 347 |
palm-2
|
1,138 | ±9 | 8,554 | — | |
| 348 |
gemma-7b-it
|
1,137 | ±9 | 8,925 | — | |
| 349 |
codellama-34b-instruct
|
Meta | 1,136 | ±9 | 7,366 | — |
| 350 | Z7 zephyr-7b-beta | Unknown | 1,130 | ±9 | 11,118 | — |
| 351 |
phi-3-mini-128k-instruct
|
Microsoft | 1,129 | ±7 | 20,685 | — |
| 352 |
Phi-3-mini-4k-instruct
|
Microsoft | 1,127 | ±6 | 20,118 | — |
| 353 | G3 guanaco-33b | Unknown | 1,127 | ±12 | 2,921 | — |
| 354 | Z7 zephyr-7b-alpha | Unknown | 1,126 | ±16 | 1,785 | — |
| 355 | SN stripedhyena-nous-7b | Unknown | 1,121 | ±11 | 5,182 | — |
| 356 |
codellama-70b-instruct
|
Meta | 1,118 | ±18 | 1,143 | — |
| 357 |
gemma-1.1-2b-it
|
1,116 | ±8 | 10,854 | — | |
| 358 | V7 vicuna-7b | Unknown | 1,114 | ±9 | 6,923 | — |
| 359 | S1 smollm2-1.7b-instruct | Unknown | 1,114 | ±14 | 2,199 | — |
| 360 |
Meta: Llama 3.2 1B Instruct
|
Meta | 1,111 | ±8 | 8,045 | — |
| 361 |
mistral-7b-instruct
|
Mistral | 1,109 | ±9 | 8,977 | — |
| 362 |
llama-2-7b-chat
|
Meta | 1,107 | ±7 | 14,148 | — |
| 363 |
gemma-2b-it
|
1,093 | ±11 | 4,780 | — | |
| 364 |
qwen1.5-4b-chat
|
Alibaba | 1,090 | ±9 | 7,597 | — |
| 365 | A2 olmo-7b-instruct | Allen Institute for AI | 1,073 | ±11 | 6,328 | — |
| 366 | K1 koala-13b | Unknown | 1,070 | ±10 | 6,965 | — |
| 367 | A1 alpaca-13b | Unknown | 1,068 | ±11 | 5,745 | — |
| 368 | G1 gpt4all-13b-snoozy | Unknown | 1,066 | ±15 | 1,743 | — |
| 369 | M7 mpt-7b-chat | Unknown | 1,062 | ±12 | 3,924 | — |
| 370 | C6 chatglm3-6b | Unknown | 1,056 | ±12 | 4,658 | — |
| 371 | R4 RWKV-4-Raven-14B | Unknown | 1,041 | ±11 | 4,845 | — |
| 372 | C6 chatglm2-6b | Unknown | 1,024 | ±14 | 2,658 | — |
| 373 | OP oasst-pythia-12b | Unknown | 1,022 | ±11 | 6,310 | — |
| 374 |
chatglm-6b
|
Z.ai | 995 | ±13 | 4,914 | — |
| 375 | FT fastchat-t5-3b | Unknown | 991 | ±12 | 4,203 | — |
| 376 | DV dolly-v2-12b | Unknown | 981 | ±14 | 3,412 | — |
| 377 |
llama-13b
|
Meta | 973 | ±16 | 2,391 | — |
| 378 | ST stablelm-tuned-alpha-7b | Unknown | 952 | ±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.