The Known Good Updated 4 Sep 2026 Subscribe
Alibaba ·Proprietary ·Released April 2026·Tracked since 25 Jul 2026

Qwen: Qwen3.6 Max Preview — quality, speed & price analysis

Compare with another model Provider benchmarks Data sources
Quality
#12 of 65
89based on 3 of 7 evaluations
Known Good Index
Speed
#176 of 338
46.4
Output tokens per second
Price
#323 of 442
$2.31
Blended per 1M tokens
In $1.03 · Out $6.16
Cache hit price
#187 of 324
$0.13
per 1M tokens (−87%)
Context
#220 of 476
262k
tokens (~400 pages)
Summary

Qwen: Qwen3.6 Max Preview is in the top quarter of the models we track for quality, and inexpensive for its standing, and notably slow. It accepts text input, outputs text, and supports a 262k-token context window.

It scores 89 on the Known Good Index, well above the tracked average of 65, from 3 of the seven component evaluations. Measured against the tracked average, its strongest result is Mock AIME 2024–25 (91 against 54) and its weakest is SWE-bench Verified (77 against 71).

Pricing is $1.03 per 1M input tokens (below the $2.07 average) and $6.16 per 1M output (below the $9.51 average). Cached input reads at $0.13 per 1M, a 87% discount on its input price. At 46 tokens per second it sits in the lower middle of the tracked range.

Generated from tracked data on 4 Sep 2026 · how these comparisons are computed →

Technical specifications
ReasoningYes
Input modalitytext
Output modalitytext
Context window262,144 tokens
Max output65,536 tokens
WeightsProprietary
Knowledge cutoffApril 2025
Tool callingYes
Providers1 host · compare →
Highlights — where Qwen: Qwen3.6 Max Preview sits
Quality

Known Good Index · Higher is better · Composite of seven published evaluations

97
97
95
93
93
93
92
89
gpt-5.5-pre-release
Gemini 3.1 Pro
Preview
Gemini 3.5 Flash
DeepSeek V4 Pro
0423
GPT-5.5
Qwen3.7 Max
Claude Opus 4.7
Qwen3.6 Max
Previewthis #12/65
Speed

Output tokens per second · Higher is better · OpenRouter endpoint telemetry

2,998
2,653
594
350
335
328
307
46
Morph V3 Fast
Relace Apply 3
Morph V3 Large
Grok 4.20
Multi-Agent
gpt-oss-safeguard-20b
Mercury 2.5
Preview
Nano Banana 2 Lite
(Gemini 3.1 Flash Lite Image)
Qwen3.6 Max
Previewthis #176/338 · below scale
Price

Blended USD per 1M tokens · Lower is better · Published pricing via OpenRouter

$0.01
$0.02
$0.03
$0.04
$0.04
$0.04
$0.05
$2.31
Ling-2.6-flash
Mistral Nemo
Ling-3.0-flash
Granite 4.0 Micro
Llama 3 8B Lunaris
Nex-N2-Mini
Solar Pro 4
Qwen3.6 Max
Previewthis #323/442 · off scale
Jump to section
Models shown

Quality

How Qwen: Qwen3.6 Max Preview compares against every tracked model

Known Good IndexCodingMathematicsReasoning
Known Good Index

Composite of GPQA Diamond, Mock AIME 2024–25, MATH Level 5, SWE-bench Verified, LiveBench, Humanity's Last Exam and Terminal-Bench, normalised 0–100. Scores are ingested from Epoch AI; we do not run these evaluations.

⇩
97
97
95
93
93
93
92
92
91
91
90
89
89
💡 A lightbulb marks a model its provider publishes as a reasoning model
The Known Good

Quality Breakdown

Qwen: Qwen3.6 Max Preview on each evaluation feeding the index, against the tracked average

Evaluation scores

Bar = Qwen: Qwen3.6 Max Preview · grey marker = average across tracked models · scores ingested from Epoch AI

GPQA Diamond87 / 64
Mock AIME 2024–2591 / 54
SWE-bench Verified77 / 71
The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Text Arena

Elo from blind pairwise votes, ingested from Arena

1446
Elo · 95% CI ±8
#49
of 406 ranked models
5k
votes counted
1460
style-controlled (#49)

Ingested 4 Sep 2026.

The Known Good

Price & Cost

Published API pricing by token type

BlendedInput vs outputQuality per dollar
Blended Price

USD per 1M tokens at a 3:1 input:output blend. Live from OpenRouter, cross-checked against models.dev. Lower is better. Ranked against the 442 models priced above zero, which is the population the chart draws; excludes 29 published at no cost (free and promotional tiers).

⇩
$0.01
$0.02
$0.03
$0.04
$0.04
$0.04
$0.05
$0.06
$0.06
$0.06
$0.06
$0.06
$0.06
$2.31
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input tokens accepted

Context windowMax output tokens
Context Window

Maximum input context from provider metadata via models.dev and OpenRouter. Higher is better.

⇩
2.00M
2.00M
2.00M
2.00M
2.00M
1.31M
1.31M
1.31M
1.31M
1.31M
1.31M
1.31M
262k
The Known Good

Speed

Mean output throughput across hosting providers, over successful measurements from the last 48 hours

Output speedBy provider
Output Speed

Mean output tokens per second across all tracked providers, over successful measurements from the last 48 hours. Derived from OpenRouter endpoint telemetry. Higher is better.

⇩
2,998
2,653
594
350
335
328
307
256
167
162
160
156
46
The Known Good

Latency

Time to first token, mean across providers over successful measurements from the last 48 hours

Latency (TTFT)

Seconds to first streamed chunk, mean across tracked providers over successful measurements from the last 48 hours. Derived from OpenRouter endpoint telemetry. Lower is better.

⇩
0.1
0.1
0.2
0.2
0.2
0.2
0.2
0.3
0.3
0.3
0.3
0.3
1.9
The Known Good

Providers

Hosts serving Qwen: Qwen3.6 Max Preview, with their own price and speed

1 provider
Full provider benchmarks →
ProviderInput $/MOutput $/M BlendedSpeedTTFTContext
Alibaba · first party $1.03 $6.16 $2.31 49 2.5s 262k

Per-host pricing and telemetry from OpenRouter. Speed is output tokens per second; TTFT is time to first token.

The Known Good

History

How price and quality have moved since we began tracking this model

Quality & price over time

Since 25 Jul 2026

Known Good Index 89 · based on 3 of 7 evaluations
Blended price $2.31 per 1M · observed 4 Sep 2026
Output speed 46 tok/s · observed 4 Sep 2026
Time to first token 1.9s

No recorded changes for this model since tracking began.

The Known Good

Comparisons

Head-to-head pages pairing Qwen: Qwen3.6 Max Preview with other tracked models

Qwen: Qwen3.6 Max Preview vs Z.ai: GLM 5.1 Qwen: Qwen3.6 Max Preview vs Anthropic: Claude Opus 4.6 Qwen: Qwen3.6 Max Preview vs Z.ai: GLM 5.2 Qwen: Qwen3.6 Max Preview vs OpenAI: GPT-5.4 Qwen: Qwen3.6 Max Preview vs MoonshotAI: Kimi K2.6 Qwen: Qwen3.6 Max Preview vs Anthropic: Claude Opus 4.7 Qwen: Qwen3.6 Max Preview vs Qwen: Qwen3.7 Max Qwen: Qwen3.6 Max Preview vs OpenAI: GPT-5.5 All 49 comparisons →
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →