Qwen·released 2024-09-181 source
Qwen2.5-Coder-0.5B 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 34.5 on GSM8K (self-reported)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| GSM8K | 34.5accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| HellaSwag | 31.2accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| MMLU | 22.67accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| ARC AI2 | 12.53accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
| Winogrande | 9.6accuracy (%) | self-reported· optimizedT1 | 2024-09-18Qwen2.5-Coder Technical Report |
Claims drawn from cited facts, not live model generation.
Developed by Qwen, this model is a compact 0.5-billion parameter release from 2024. That small scale implies greater efficiency and lower cost, though with less performance headroom than larger or frontier-scale models.
4 cited facts
This model is tracked across 5 benchmarks and currently holds no top score. These figures are self-reported: they are vendor-claimed and not yet independently confirmed, so treat them as claims rather than verified results.
3 cited facts
With an average gap of 66.3 points to the benchmark leader under the disclosed harness, this model sits in a wide-gap band — well behind the front of the pack. It does not hold the top score on any tracked benchmark, so it has no category-leadership position yet.
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-0.5B 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-0.5B has recorded scores on 5 benchmarks, each shown with its evidence status.
Qwen2.5-Coder-0.5B 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-0.5B has 5 tracked claims: 5 self-reported.