Claude Sonnet 5 (Thinking) — benchmark results
Provider: Anthropic. Released 2026-06-30. Access: API.
Unified ELO 1858 ± 49, rank #83 of 1719 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chatbot Arena (Code) | 1551 | Elo | 94.4 |
| Chatbot Arena (Text) | 1464 | Elo | 91.5 |
| Agent Arena - Confirmed Success | 12.24 | Confirmed Success (%) | 86.7 |
| Chatbot Arena (Vision) | 1263 | Arena Score | 84.8 |
| PM-LLM-Benchmark | 33.3 | Score | 74.8 |
| Agent Arena - Praise vs Complaint | 13.43 | Praise vs Complaint (%) | 73.3 |
| Chatbot Arena (Document) | 1476 | Elo | 67.7 |
| Agent Arena - Tool Hallucination | 1.14 | Tool Hallucination (%) | 61.7 |
| Agent Arena | 7.38 | Net Improvement (%) | 56.7 |
| Agent Arena - Bash Recovery | 9.15 | Bash Recovery (%) | 53.3 |
| Agent Arena - Steerability | 0.95 | Steerability (%) | 3.3 |
Interactive version: aibenchmarks.dev/model?slug=claude-sonnet-5-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-07.