Claude Sonnet 5 (High) — benchmark results
Provider: Anthropic. Released 2026-06-30. Access: API.
Unified ELO 1914 ± 26, rank #45 of 1726 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chatbot Arena (Code) | 1551 | Elo | 94.4 |
| Chatbot Arena (Text) | 1464 | Elo | 91.5 |
| WeirdML | 68.78 | Average Score | 88.1 |
| Agent Arena - Confirmed Success | 11.79 | Confirmed Success (%) | 85.7 |
| Chatbot Arena (Vision) | 1263 | Arena Score | 84.8 |
| Mercor APEX | 32.5 | Best Pass@1 (%) | 80.9 |
| Agent Arena - Praise vs Complaint | 14 | Praise vs Complaint (%) | 75 |
| Opus Magnum Bench | 26.55 | Human-normalized score (%) | 70.6 |
| Agent Arena - Tool Hallucination | 1.11 | Tool Hallucination (%) | 67.9 |
| Chatbot Arena (Document) | 1476 | Elo | 67.7 |
| Agent Arena | 7.72 | Net Improvement (%) | 57.1 |
| CursorBench 3.1 | 57 | Score (%) | 54.2 |
Interactive version: aibenchmarks.dev/model?slug=claude-sonnet-5-high · How the rankings work · Data refreshed daily, snapshot 2026-07-08.