Qwen3 Max
Qwen · released Sep 23, 2025
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...
Specification
- Context window
- 262K
- Max output
- 66K
- Knowledge cutoff
- Jun 30, 2025
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
24.5
67th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
29 t/s
Median across providers
Latency
1.04s
Time to first token
Cost per task
$0.14
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- MMLU-Pro84.1%
- AIME 202580.7%
- LiveCodeBench76.7%
- GPQA Diamond76.4%
- τ²-bench (Telecom)74.3%
- AA-LCR (long context)48.3%
- IFBench44.1%
- SciCode38.3%
- Terminal-Bench Hard20.5%
- Humanity's Last Exam11.9%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 84.1% |
| AIME 2025 | 80.7% |
| LiveCodeBench | 76.7% |
| GPQA Diamond | 76.4% |
| τ²-bench (Telecom) | 74.3% |
| AA-LCR (long context) | 48.3% |
| IFBench | 44.1% |
| SciCode | 38.3% |
| Terminal-Bench Hard | 20.5% |
| Humanity's Last Exam | 11.9% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Gemini 3.1 Flash LiteGoogle25.6
- V3.2DeepSeek25.1
- Qwen3 MaxQwen24.5
- Ling 3.0 Tiny (free)InclusionAI24.3
- Claude Haiku 4.5Anthropic24.1
- gpt-oss-120bOpenAI24.1
- Kimi K2 0905Moonshot AI24.0
- o1OpenAI23.9
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Gemini 3.1 Flash Lite | 25.6 |
| V3.2 | 25.1 |
| Qwen3 Max | 24.5 |
| Ling 3.0 Tiny (free) | 24.3 |
| Claude Haiku 4.5 | 24.1 |
| gpt-oss-120b | 24.1 |
| Kimi K2 0905 | 24.0 |
| o1 | 23.9 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.78
- Output / 1M tokens
- $3.9
- Cached input / 1M
- $0.156
- Blended 3:1
- $1.56
One task, estimated
$0.14
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,141
- Win rate
- 44.5%
- Strongest at
- Websites
- Tournaments
- 22,600
Elo by category
Dot position on a 1,050–1,150 scale · Elo has no meaningful zero
- 1,141
- 1,136
- 1,129
- 1,126
- 1,113
- 1,058
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Websites | 1141 | 44.5% |
| Game development | 1136 | 43.9% |
| 3D scenes | 1129 | 43.5% |
| Data visualisation | 1126 | 41.1% |
| UI components | 1113 | 40.2% |
| SVG | 1058 | 37.3% |