OpenHathi-7B-Hi-v0.1-Base: benchmark results
Provider: Other. Access: Open.
Unified ELO 1325 ± 19, rank #2599 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 71.27 | Accuracy (%) (5-shot) | 26.3 |
| Open LLM Leaderboard v1 - GSM8K | 5.91 | Accuracy (%) (5-shot) | 24.9 |
| Open LLM Leaderboard v1 - HellaSwag | 74.34 | Normalized accuracy (%) (10-shot) | 24.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.49 | Normalized accuracy (%) (25-shot) | 24 |
| Open LLM Leaderboard v1 - MMLU | 41.38 | Accuracy (%) (5-shot) | 21.6 |
| Open LLM Leaderboard - MuSR | 36.58 | Score | 21.1 |
| Open LLM Leaderboard - BBH | 33.54 | Score | 17 |
| Open LLM Leaderboard - MMLU-Pro | 15.43 | Score | 13.7 |
| Open LLM Leaderboard - IFEval | 18.04 | Score | 9.3 |
| Open LLM Leaderboard - GPQA | 25.34 | Score | 6.9 |
| Open LLM Leaderboard - MATH Level 5 | 0.83 | Score | 6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.46 | MC2 (%) (0-shot) | 5.9 |
Interactive version: theaggregate.ai/model?slug=openhathi-7b-hi-v0-1-base · How It Works · Data refreshed daily, snapshot 2026-09-23.