DeepSeekDeepSeek-R1-Distill-Qwen-1.5B
Best configuration ranks #580 of 610 on the BenchLeader Index at 36.4 ±5.2. Last measured 20 Jan 2025stale: no new result in six months. Released 20 Jan 2025.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Overall index36
- Reasoning27
- Maths33
- Instruction following19
- Long context25
- Composite36
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 | 33.6%#244 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | 9.8%#525 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 3.1%#514 | Artificial Analysis |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 21.4%#202 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 13.2%#400 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 1.7%#418 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 5.5#485 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.