StarCoder 2 15B
StarCoder 2 15B.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
StarCoder 2 15B
Open weights
96.3
#224 of 256
Epoch Capabilities Index
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 | 64.1% | #36 of 85 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| ARC-Challenge | 47.2% | #50 of 75 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| WinoGrande | 64.3% | #62 of 76 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 57.7% | #30 of 70 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CRUXEval | 47.1% | #5 of 11 | Official leaderboard | |
| MultiPL-E | 34.9% | #6 of 9 | Official leaderboard | |
| HumanEval | 46.3% | #34 of 46 | Official leaderboard | |
| HumanEval+ | 37.8% | #35 of 46 | Official leaderboard |
Hugging Face's models over time
Hugging Face'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)