StarCoder2-15B-Instruct-v0.1: benchmark results
Provider: BigCode.
Aggregate Rating 1389 ± 49, rank #6541 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EvalPlus (HumanEval+ & MBPP+) | 62.8 | Pass@1 avg (%) | 63.7 |
| BigCodeBench | 37.6 | Pass@1 (%) | 45.6 |
| FullStackBench (2024-12 bilingual) | 41.79 | Pass@1 (%), 3,374 problems: 1,687 English and 1,687 Chinese; | 26.9 |
| C3-Bench (Controllable Code Completion) - Implementation Control - Pass@1 | 36.6 | Pass@1 (%; unit tests on the 1,286 instructed ICC tasks) | 17.5 |
| CodeElo | 129 | Elo Rating | 14.7 |
| C3-Bench (Controllable Code Completion) - Implementation Control | 4.2 | Instruction-Following Rate (%; 1,286 ICC tasks: passes the u | 7.5 |
| C3-Bench (Controllable Code Completion) - Scale Control | 1.6 | Instruction-Following Rate (%; 909 SCC tasks: AST node-type | 0 |
Interactive version: theaggregate.ai/model?slug=starcoder2-15b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.