gpt2-xl-sft: benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1126 ± 34, rank #10420 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 0.76 | Accuracy (%) (5-shot) | 14 |
| Open LLM Leaderboard v1 - HellaSwag | 49.17 | Normalized accuracy (%) (10-shot) | 10 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.78 | MC2 (%) (0-shot) | 9.2 |
| Open LLM Leaderboard v1 - WinoGrande | 55.56 | Accuracy (%) (5-shot) | 9.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 30.03 | Normalized accuracy (%) (25-shot) | 9.1 |
| Open LLM Leaderboard v1 - MMLU | 25.56 | Accuracy (%) (5-shot) | 8.9 |
Interactive version: theaggregate.ai/model?slug=gpt2-xl-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.