gpt2_137m_DolphinCoder [Adapter] (Publisher: Zangs3011): benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1105 ± 40, rank #10654 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.58 | MC2 (%) (0-shot) | 17.5 |
| Open LLM Leaderboard v1 - GSM8K | 1.06 | Accuracy (%) (5-shot) | 15.4 |
| Open LLM Leaderboard v1 - MMLU | 25.4 | Accuracy (%) (5-shot) | 8.1 |
| Open LLM Leaderboard v1 - WinoGrande | 52.01 | Accuracy (%) (5-shot) | 6.3 |
| Open LLM Leaderboard v1 - HellaSwag | 31.35 | Normalized accuracy (%) (10-shot) | 6.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 21.84 | Normalized accuracy (%) (25-shot) | 0.7 |
Interactive version: theaggregate.ai/model?slug=gpt2-137m-dolphincoder-adapter-publisher-zangs3011 · How It Works · Data refreshed daily, snapshot 2026-11-08.