OpenBioLLM-Llama3-70B: benchmark results
Provider: Saama AI Labs. Released 2024-04-24. Access: Open.
Aggregate Rating 1502 ± 24, rank #2325 of 10916 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 75.97 | Score | 91.4 |
| Open LLM Leaderboard - BBH | 63.99 | Score | 88.6 |
| Open LLM Leaderboard - MMLU-Pro | 48.67 | Score | 86.9 |
| RABBITS B4B | 78.76 | Accuracy (%) | 83.3 |
| ADRD-Bench - Unified QA | 91.79 | Exact-match accuracy (0-1, shown times 100) on the 1,438 Alz | 82.9 |
| CureMed-Bench - Language Consistency | 70.3 | Language consistency (%; share of final answers written in t | 79.2 |
| Open LLM Leaderboard - MuSR | 44.17 | Score | 79.1 |
| Open LLM Leaderboard - GPQA | 32.3 | Score | 77 |
| CureMed-Bench | 51.22 | Logical accuracy (%; share of final answers a GPT-4o judge m | 75 |
| Open LLM Leaderboard - MATH Level 5 | 19.71 | Score | 70.4 |
| RABBITS MedQA Original | 75.4 | Accuracy (%) | 66 |
| ADRD-Bench - Caregiving QA | 89.93 | Exact-match accuracy (0-1, shown times 100) on 149 caregivin | 60.3 |
Interactive version: theaggregate.ai/model?slug=openbiollm-llama3-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.