Back to BenchmarksFrontier
ScienceQA
Science question answering across multiple domains
Leaderboard
(8 models)| Rank | Model | Score | Stderr |
|---|---|---|---|
| 1 | Phi-3-mini-4k-instruct | 91.30 | — |
| 2 | GPT-4o | 88.50 | — |
| 3 | Gemini 1.5 Flash | 79.70 | — |
| 4 | falcon-180B | 74.90 | — |
| 5 | Llama 3.1 405B | 73.70 | — |
| 6 | Claude 3.7 Sonnet | 72.00 | — |
| 7 | Qwen Plus | 68.20 | — |
| 8 | Llama-2-7b | 55.78 | — |
Data source: Epoch AI, “Data on AI Benchmarking”. Published at epoch.ai
Licensed under CC-BY 4.0