Instruct_GPT: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1121 ± 38, rank #10506 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 26.84 | Accuracy (%) (5-shot) | 13.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.72 | MC2 (%) (0-shot) | 11.8 |
| Open LLM Leaderboard v1 - GSM8K | 0.3 | Accuracy (%) (5-shot) | 11.4 |
| Open LLM Leaderboard v1 - WinoGrande | 54.3 | Accuracy (%) (5-shot) | 8.4 |
| Open LLM Leaderboard v1 - HellaSwag | 39.33 | Normalized accuracy (%) (10-shot) | 7.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 28.24 | Normalized accuracy (%) (25-shot) | 7.5 |
Interactive version: theaggregate.ai/model?slug=instruct-gpt · How It Works · Data refreshed daily, snapshot 2026-11-08.