cosmo-1B [float16] [rev: ffb89c545ae2]: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1164 ± 36, rank #9802 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 5.53 | Accuracy (%) (5-shot) | 24.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 38.57 | Normalized accuracy (%) (25-shot) | 15.2 |
| Open LLM Leaderboard v1 - MMLU | 26.69 | Accuracy (%) (5-shot) | 13.4 |
| Open LLM Leaderboard v1 - HellaSwag | 55.13 | Normalized accuracy (%) (10-shot) | 12.3 |
| Open LLM Leaderboard v1 - WinoGrande | 55.49 | Accuracy (%) (5-shot) | 9.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.15 | MC2 (%) (0-shot) | 7.5 |
Interactive version: theaggregate.ai/model?slug=cosmo-1b-float16-rev-ffb89c545ae2 · How It Works · Data refreshed daily, snapshot 2026-11-08.