proofGPT-v0.1-6.7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1093 ± 43, rank #10786 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.87 | MC2 (%) (0-shot) | 49.8 |
| Open LLM Leaderboard v1 - WinoGrande | 51.14 | Accuracy (%) (5-shot) | 5 |
| Open LLM Leaderboard v1 - HellaSwag | 28.45 | Normalized accuracy (%) (10-shot) | 4.7 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - MMLU | 24.57 | Accuracy (%) (5-shot) | 4.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 23.29 | Normalized accuracy (%) (25-shot) | 2.5 |
Interactive version: theaggregate.ai/model?slug=proofgpt-v0-1-6-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.