Qwen2.5-Coder (1.5B)
Qwen2.5-Coder (1.5B).
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Sep 2024 Qwen2.5-Coder (1.5B)
Open weights
89.3
#230 of 256
Epoch Capabilities Index
- BigCodeBench-Hard 5.80% #89 /96
- AutoCodeBench 10.3% #34 /34
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU | 53.6% | #55 of 85 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| ARC-Challenge | 45.2% | #52 of 75 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| HellaSwag | 61.8% | #54 of 63 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| WinoGrande | 60.7% | #67 of 76 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 65.8% | #26 of 70 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 29.9% | #61 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 5.80% | #89 of 96 | Official leaderboard | |
| AutoCodeBench | 10.3% | #34 of 34 | Official leaderboard |
Qwen's models over time
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)