Anthropic
Claude Opus 4.8 benchmark results
10 results on 7 benchmarks from 3 sources.
Also listed as: claude-opus-4-8-high · claude-opus-4-8 · claude-opus-4-8_none · claude-opus-4-8_low · claude-opus-4-8_max · Claude Opus 4.8 (max)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1481 | 25 | Overall, style control on; 64177 votes; 95% CI 1478–1485“claude-opus-4-8-high” | Official leaderboard | Oct 8, 2026 |
| LMArena Text | 1474 | 40 | Overall, style control on; 65259 votes; 95% CI 1470–1478“claude-opus-4-8” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1556 | 37 | Overall; 18534 votes; 95% CI 1550–1562“claude-opus-4-8-high” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1536 | 46 | Overall; 17435 votes; 95% CI 1530–1541“claude-opus-4-8” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1286 | 17 | Overall, style control on; 18350 votes; 95% CI 1280–1293“claude-opus-4-8-high” | Official leaderboard | Oct 2, 2026 |
| LMArena Vision | 1279 | 26 | Overall, style control on; 18857 votes; 95% CI 1273–1286“claude-opus-4-8” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 85.3% | 82 | Epoch AI run, accuracy | Independent run | Aug 6, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 84.4% | 95 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 6, 2026 |
| OSWorld 2.0 | 20.6% | 7 | Binary accuracy; 500 steps; reasoning: max | Official leaderboard via Epoch AI | May 28, 2026 |
| τ²-bench | 39.7% | 8 | banking_knowledge domain, pass^1; effort: max; submitted by Sierra; v1.0.1 | Official leaderboard | Jul 23, 2026 |
FAQ
Where do these Claude Opus 4.8 scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.