Airavata: benchmark results
Provider: AI4Bharat. Released 2024-01-13. Access: Open.
Aggregate Rating 1248 ± 30, rank #9271 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - GPQA | 27.43 | Score | 29.4 |
| Open LLM Leaderboard - MuSR | 37.63 | Score | 27.5 |
| Open LLM Leaderboard v1 - MMLU | 43.9 | Accuracy (%) (5-shot) | 23 |
| Open LLM Leaderboard v1 - WinoGrande | 68.82 | Accuracy (%) (5-shot) | 22.9 |
| Open LLM Leaderboard v1 - GSM8K | 4.02 | Accuracy (%) (5-shot) | 22.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 46.5 | Normalized accuracy (%) (25-shot) | 21.6 |
| Open LLM Leaderboard - BBH | 36.28 | Score | 20.7 |
| Open LLM Leaderboard v1 - HellaSwag | 69.26 | Normalized accuracy (%) (10-shot) | 19.9 |
| Open LLM Leaderboard - MMLU-Pro | 16.35 | Score | 17 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.62 | MC2 (%) (0-shot) | 14.7 |
| Open LLM Leaderboard - MATH Level 5 | 1.81 | Score | 12.8 |
| HindiGen | 9.57 | 3C3H Score (%) | 2.9 |
Interactive version: theaggregate.ai/model?slug=airavata · How It Works · Data refreshed daily, snapshot 2026-11-08.