AlibabaQwQ-32B
Best configuration ranks #385 of 610 on the BenchLeader Index at 45.7 ±4.0. Last measured 2 Sept 2026. Released 1 Dec 2024.
- Blended price
- $0.431/M
- $0.287 in · $0.861 out
- Output speed
- –
- First answer
- –
- Context
- 131k
- Overall index46
- Reasoning49
- Coding40
- Maths50
- Instruction following41
- Human preference51
- Long context39
- Composite41
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 | default | Source |
|---|---|---|
| GPQA Diamond | 65.3%#169 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1356#188 | LMArena |
| GPQA Diamond (AA)not in index | 59.3%#361 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 7.3%#297 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1384#189 | LMArena |
| Aider Polyglot | 20.9%#36 | Aider polyglot leaderboard |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 59.2%#148 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 38.8%#265 | Artificial Analysis |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1336#195 | LMArena |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 26.7%#334 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 137.6#108 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | 9.5#327 | Artificial Analysis |
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0004 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.0040 | – | – |
| Code edit | 6,000 / 1,500 | $0.0030 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.021 | – | – |
| Structured extraction | 2,000 / 200 | $0.0007 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.