cosmo-3B-test-v0.2: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1148 ± 34, rank #9990 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 1.52 | Accuracy (%) (5-shot) | 17.3 |
| Open LLM Leaderboard v1 - MMLU | 27.33 | Accuracy (%) (5-shot) | 15 |
| Open LLM Leaderboard v1 - ARC Challenge | 35.32 | Normalized accuracy (%) (25-shot) | 13 |
| Open LLM Leaderboard v1 - HellaSwag | 51.7 | Normalized accuracy (%) (10-shot) | 10.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.82 | MC2 (%) (0-shot) | 9.2 |
| Open LLM Leaderboard v1 - WinoGrande | 53.51 | Accuracy (%) (5-shot) | 7.8 |
Interactive version: theaggregate.ai/model?slug=cosmo-3b-test-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.