GPT-2-Large-32k-steps: benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1084 ± 43, rank #10857 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.25 | MC2 (%) (0-shot) | 44.2 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - HellaSwag | 26.39 | Normalized accuracy (%) (10-shot) | 3 |
| Open LLM Leaderboard v1 - MMLU | 23.73 | Accuracy (%) (5-shot) | 2.3 |
| Open LLM Leaderboard v1 - WinoGrande | 49.64 | Accuracy (%) (5-shot) | 2.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 22.53 | Normalized accuracy (%) (25-shot) | 1.2 |
Interactive version: theaggregate.ai/model?slug=gpt-2-large-32k-steps · How It Works · Data refreshed daily, snapshot 2026-11-08.