pooled_gqa_mix_chatml: benchmark results
Provider: Other.
Aggregate Rating 1156 ± 36, rank #9870 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.98 | MC2 (%) (0-shot) | 36 |
| Open LLM Leaderboard v1 - GSM8K | 1.9 | Accuracy (%) (5-shot) | 18.7 |
| Open LLM Leaderboard v1 - HellaSwag | 61.23 | Normalized accuracy (%) (10-shot) | 15.3 |
| Open LLM Leaderboard v1 - MMLU | 26.86 | Accuracy (%) (5-shot) | 14 |
| Open LLM Leaderboard v1 - ARC Challenge | 36.18 | Normalized accuracy (%) (25-shot) | 13.7 |
| Open LLM Leaderboard v1 - WinoGrande | 50.75 | Accuracy (%) (5-shot) | 4.2 |
Interactive version: theaggregate.ai/model?slug=pooled-gqa-mix-chatml · How It Works · Data refreshed daily, snapshot 2026-11-08.