pooled_gqa_raw: benchmark results
Provider: Other.
Aggregate Rating 1116 ± 36, rank #10564 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.02 | MC2 (%) (0-shot) | 12.7 |
| Open LLM Leaderboard v1 - HellaSwag | 53.48 | Normalized accuracy (%) (10-shot) | 11.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 29.35 | Normalized accuracy (%) (25-shot) | 8.5 |
| Open LLM Leaderboard v1 - MMLU | 24.69 | Accuracy (%) (5-shot) | 4.7 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - WinoGrande | 50.67 | Accuracy (%) (5-shot) | 4.1 |
Interactive version: theaggregate.ai/model?slug=pooled-gqa-raw · How It Works · Data refreshed daily, snapshot 2026-11-08.