code_gpt2: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1092 ± 43, rank #10791 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.6 | MC2 (%) (0-shot) | 14.7 |
| Open LLM Leaderboard v1 - MMLU | 25.03 | Accuracy (%) (5-shot) | 6.1 |
| Open LLM Leaderboard v1 - HellaSwag | 30.99 | Normalized accuracy (%) (10-shot) | 5.8 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 23.29 | Normalized accuracy (%) (25-shot) | 2.5 |
| Open LLM Leaderboard v1 - WinoGrande | 49.25 | Accuracy (%) (5-shot) | 1.1 |
Interactive version: theaggregate.ai/model?slug=code-gpt2 · How It Works · Data refreshed daily, snapshot 2026-11-08.