Qwen·released 2024-09-181 source
Qwen2.5-Coder-32B benchmark scores: 5 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 91.1 on GSM8K (self-reported)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| GSM8K | 91.1accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| HellaSwag | 77.33accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| MMLU | 72.13accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| Winogrande | 61.6accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| ARC AI2 | 60.67accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
Claims drawn from cited facts, not live model generation.
This model was developed by Qwen and released in 2024. Its 32 billion parameters put it at the large end of the scale, offering more headroom but demanding greater compute and expense than compact alternatives.
3 cited facts
This model is tracked on five benchmarks. It holds no current top score on any of them. These results are self-reported and not yet independently confirmed, so treat them as claims rather than verified results.
3 cited facts
Relative to the disclosed harness, it trails the leader by an average of 15.83 points, a wide gap that places it well behind the front of the pack. With no benchmark where it holds the top score, it does not currently show category leadership.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
Qwen2.5-Coder-32B is an AI model developed by Qwen, released 2024-09-18. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen2.5-Coder-32B has recorded scores on 5 benchmarks, each shown with its evidence status.
Qwen2.5-Coder-32B has recorded scores on 5 benchmarks — Winogrande, MMLU, ARC AI2, GSM8K, HellaSwag. The full table above shows each score with its evidence status.
0 of 5 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Qwen2.5-Coder-32B has 5 tracked claims: 5 self-reported.