AlibabaAuto-detectedQwen3 7
Best configuration ranks #114 of 610 on the BenchLeader Index at 58.9 ±4.0 (max reasoning effort). Last measured 8 Sept 2026. Released 19 May 2026.
- Blended price
- $3.75/M
- $2.50 in · $7.50 out
- Output speed
- 199 tok/s
- First answer
- 14 s
- first token 1.03 s
- Context
- 1M
- Overall index59
- Reasoning66
- Coding61
- Agents & tools56
- Maths57
- Knowledge64
- Instruction following77
- Human preference37
- Long context66
- Composite56
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| maxbest | 58.9 | #114 | 199 tok/s | 14 s | $0.0033 | Agents & tools 56 · Coding 61 · Composite 56 · Human preference 37 · Instruction following 77 · Knowledge 64 · Long context 66 · Maths 57 · Reasoning 66 |
| default | – | – | 53 tok/s | 1.03 s | – | Coding 67 · Human preference 67 · Reasoning 67 |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| GPQA Diamond | 90.9%#29 | – | Epoch AI Benchmarking Hub | |
| SimpleBench | 70.4%#13 | – | SimpleBench | |
| LMArena Hard Prompts | – | 1495#34 | LMArena | |
| LiveBench Reasoningnot in index | 83.3%#32 | – | LiveBench | |
| GPQA Diamond (AA)not in index | 92.3%#36 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 40.5%#53 | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 90.2%#25 | – | Vals AI |
Coding
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| SWE-bench Verified (Epoch) | 77.3%#7 | – | Epoch AI Benchmarking Hub | |
| SciCode | 48.8%#67 | – | SciCode | |
| LMArena Coding | – | 1525#19 | LMArena | |
| LMArena WebDev | 1517#36 | – | LMArena | |
| LiveBench Codingnot in index | 74.2%#39 | – | LiveBench | |
| SciCode (AA)not in index | 49.5%#74 | – | Artificial Analysis | |
| LiveCodeBench | 87.1%#18 | – | Vals AI | |
| IOI | 46.8%#11 | – | Vals AI | |
| SWE-bench (Vals)not in index | 68.8%#66 | – | Vals AI |
Agents & tools
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| LMArena Agent | -3.1#30 | – | LMArena | |
| LiveBench Agentic Codingnot in index | 43.6%#43 | – | LiveBench | |
| Terminal-Bench Hard | 50.8%#22 | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 94.7%#30 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (Vals) | 61.0%#31 | – | Vals AI |
Maths
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 64.6%#24 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 34.1%#24 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 95.6%#29 | – | Epoch AI Benchmarking Hub | |
| ProofBench | 26.0%#30 | – | Vals AI | |
| LiveBench Mathematicsnot in index | 85.3%#40 | – | LiveBench |
Knowledge
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| SimpleQA Verified | 55.8%#15 | – | Epoch AI Benchmarking Hub | |
| LiveBench Data Analysisnot in index | 71.8%#34 | – | LiveBench | |
| AA-Omniscience | 13.5#59 | – | Artificial Analysis | |
| MMLU-Pro | 89.3%#12 | – | Vals AI | |
| LegalBench | 84.9%#25 | – | Vals AI | |
| CorpFin | 63.7%#41 | – | Vals AI | |
| TaxEval | 75.3%#19 | – | Vals AI |
Instruction following
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| LiveBench Languagenot in index | 79.7%#24 | – | LiveBench | |
| IFBench | 80.5%#7 | – | Artificial Analysis |
Human preference
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| LMArena Text | – | 1474#32 | LMArena | |
| EQ-Bench 4 | 1110#22 | – | EQ-Bench |
Long context
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| AA-LCR | 79.0%#71 | – | Artificial Analysis |
Composite
| Benchmark | max | default | Source | Trend |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | 153.7#31 | – | Epoch AI Benchmarking Hub | |
| LiveBench | 73.1%#37 | – | LiveBench | |
| AA Intelligence Index | 29.9#82 | – | Artificial Analysis | |
| Vals Indexnot in index | 44.8#31 | – | Vals AI |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Alibaba Cloud Int. | 53 tok/s | 1.03 s | $1.48 | $4.42 | 1M | – |
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.500 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0033 | $0.0027 | 15.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.035 | $0.017 | 17.4 s |
| Code edit | 6,000 / 1,500 | $0.026 | $0.017 | 21.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.180 | $0.090 | 34.4 s |
| Structured extraction | 2,000 / 200 | $0.0065 | $0.0035 | 15.4 s |
See also
Data as of 9 Sept 2026. Compare these configurations.