UNA-POLAR-10.7B-InstructMath-v2: benchmark results
Provider: fblgit. Access: Open.
Aggregate Rating 1459 ± 37, rank #3393 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.73 | MC2 (%) (0-shot) | 92.1 |
| Open LLM Leaderboard v1 - HellaSwag | 88.2 | Normalized accuracy (%) (10-shot) | 90.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.73 | Normalized accuracy (%) (25-shot) | 86.8 |
| Open LLM Leaderboard v1 - WinoGrande | 82.95 | Accuracy (%) (5-shot) | 86.4 |
| Open LLM Leaderboard v1 - MMLU | 66.03 | Accuracy (%) (5-shot) | 85.8 |
| Open LLM Leaderboard v1 - GSM8K | 64.75 | Accuracy (%) (5-shot) | 78.9 |
Interactive version: theaggregate.ai/model?slug=una-polar-10-7b-instructmath-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.