Qwen3 Max Thinking
Qwen · released Feb 9, 2026
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
Specification
- Context window
- 262K
- Max output
- 66K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
Intelligence
32.5
78th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
31 t/s
Median across providers
Latency
1.14s
Time to first token
Cost per task
$0.35
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
- GPQA Diamond86.1%
- τ²-bench (Telecom)83.6%
- IFBench70.7%
- AA-LCR (long context)70.3%
- SciCode43.1%
- Humanity's Last Exam28.0%
- Terminal-Bench Hard24.2%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 86.1% |
| τ²-bench (Telecom) | 83.6% |
| IFBench | 70.7% |
| AA-LCR (long context) | 70.3% |
| SciCode | 43.1% |
| Humanity's Last Exam | 28.0% |
| Terminal-Bench Hard | 24.2% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- LongCat 2.0Meituan33.9
- Kimi K2 ThinkingMoonshot AI33.5
- o3 ProOpenAI33.3
- 32.8
- Qwen3 Max ThinkingQwen32.5
- Qwen3.6 35B A3BQwen32.1
- M2.1MiniMax32.1
- GPT-5.1-Codex-MiniOpenAI31.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| LongCat 2.0 | 33.9 |
| Kimi K2 Thinking | 33.5 |
| o3 Pro | 33.3 |
| Qwen3.5-122B-A10B | 32.8 |
| Qwen3 Max Thinking | 32.5 |
| Qwen3.6 35B A3B | 32.1 |
| M2.1 | 32.1 |
| GPT-5.1-Codex-Mini | 31.3 |
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
- Not offered
- Blended 3:1
- $1.56
One task, estimated
$0.35
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
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.