Anthropic
Claude 3 Sonnet benchmark results
7 results on 7 benchmarks from 3 sources.
Closed Released: Feb 29, 2024 Updated Oct 22, 2026
Also listed as: claude-3-sonnet-20240229 · Claude 3 Sonnet (20240229) · Claude-3-Sonnet
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1281 | 300 | Overall, style control on; 109284 votes; 95% CI 1277–1285“claude-3-sonnet-20240229” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1016 | 146 | Overall, style control on; 12314 votes; 95% CI 1005–1028“claude-3-sonnet-20240229” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 40.6% | 237 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU | 75.9% | 37 | Exact match; 5-shot | Official leaderboard via Epoch AI | Feb 29, 2024 |
| MMLU-Pro | 56.8% | 147 | Overall accuracy; data source: TIGER-Lab“Claude-3-Sonnet” | Official leaderboard | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 2.5% | 244 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Feb 25, 2025 |
| MATH Level 5 | 18.2% | 88 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these Claude 3 Sonnet scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.