AlibabaAuto-detectedQwen3-1.7B
Best configuration ranks #557 of 610 on the BenchLeader Index at 37.8 ±3.5 (thinking reasoning effort). Released 29 Apr 2025.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 32k
- Overall index38
- Agents & tools34
- Knowledge27
- Instruction following31
- Long context25
- Composite36
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 |
|---|---|---|---|---|---|---|
| no reasoning | – | – | – | – | – | Maths 27 · Reasoning 25 |
| thinkingbest | 37.8 | #557 | – | – | – | Agents & tools 34 · Composite 36 · Instruction following 31 · Knowledge 27 · Long context 25 |
| default | 35.8 | #591 | – | – | – | Agents & tools 39 · Composite 35 · Instruction following 26 · Knowledge 24 · Long context 25 · Reasoning 30 |
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 | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| GPQA Diamond | 30.6%#249 | – | 38.0%#234 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | – | 35.6%#465 | 28.3%#499 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | – | 4.6%#404 | 5.3%#358 | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| Terminal-Bench Hard | – | 0.0%#345 | 0.0%#345 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | – | 26.0%#277 | 21.6%#305 | Artificial Analysis |
| BFCL Overall | – | – | 28.4%#53 | Berkeley Function Calling Leaderboard |
Maths
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| OTIS Mock AIME | 8.1%#213 | – | – | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| AA-Omniscience | – | -77.5#455 | -84.1#468 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| IFBench | – | 26.9%#363 | 21.1%#389 | Artificial Analysis |
Long context
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| AA-LCR | – | 0.0%#419 | 0.0%#419 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| AA Intelligence Index | – | 5.2#509 | 4.9#524 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare these configurations.