habib-DPO-v3: benchmark results
Provider: Other.
Aggregate Rating 1430 ± 32, rank #4669 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 65.2 | MC2 (%) (0-shot) | 83.3 |
| Open LLM Leaderboard v1 - HellaSwag | 86.66 | Normalized accuracy (%) (10-shot) | 82.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.86 | Normalized accuracy (%) (25-shot) | 81.6 |
| Open LLM Leaderboard v1 - GSM8K | 65.66 | Accuracy (%) (5-shot) | 80.4 |
| Open CoT - LogiQA | 5.75 | CoT Gain (%) | 70.6 |
| Open LLM Leaderboard v1 - WinoGrande | 79.32 | Accuracy (%) (5-shot) | 68.6 |
| Open LLM Leaderboard v1 - MMLU | 64.15 | Accuracy (%) (5-shot) | 66.2 |
| Open CoT - LSAT Reading Comprehension | 14.13 | CoT Gain (%) | 59.9 |
| Open CoT Leaderboard | 7.46 | Average CoT Gain (%) | 52.7 |
| Open CoT - LSAT Logical Reasoning | 9.8 | CoT Gain (%) | 46.9 |
| Open CoT - LSAT Analytical Reasoning | 3.04 | CoT Gain (%) | 41.2 |
| Open CoT - LogiQA 2 | 4.58 | CoT Gain (%) | 36.3 |
Interactive version: theaggregate.ai/model?slug=habib-dpo-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.