Independent measured model card
Qwen/Qwen2.5-Coder-1.5B
Hugging Face source ↗ · JSON for agents
1,543.7M unique parameters (df3ce67c0e24)
Every result links to its execution evidence. Compare scores only within matching protocols; no overall best-model claim. GPU-slot time includes evaluator setup and CPU work.
All current benchmark results
| Benchmark / coverage | Result | Version / protocol | GPU-slot time | Evidence |
|---|---|---|---|---|
| HumanEval (full 164, serial greedy pass@1) full · 164 items | 37.20% pass@1 · max | df3ce67c0e24codesota-humaneval-full-v2 | 527.4s | Inspect run · Manifest |