Flagship Claude model for deep reasoning, coding, and long-horizon agents
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 40.8 | thinking | independent | aa | Jul 24, 2026 |
| 34.7 | — | independent | aa | Jul 24, 2026 | ||
| Design Arena — 3d | preference | 1273 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — androidnative | preference | 1164 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — asciiart | preference | 1230 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — codecategories | preference | 1275 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — dataviz | preference | 1276 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — fullstack | preference | 1215 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — gamedev | preference | 1288 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — mobileapps | preference | 1254 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — svg | preference | 1229 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — uicomponent | preference | 1278 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — webapps | preference | 1216 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — website | preference | 1274 | — | mirror | openrouter | Jul 23, 2026 |
| LMArena Text | preference | 1463 | thinking-32k | crowd | lmarena | Jul 21, 2026 |
| 1460 | — | crowd | lmarena | Jul 21, 2026 | ||
| LMArena WebDev | preference | 1490 | thinking-32k | crowd | lmarena | Jul 21, 2026 |
| 1466 | — | crowd | lmarena | Jul 21, 2026 | ||
| Median output speed | speed | 46 tok/s | thinking | independent | aa | Jul 24, 2026 |
| 45 tok/s | — | independent | aa | Jul 24, 2026 | ||
| Median time to first token | speed | 14.17s | thinking | independent | aa | Jul 24, 2026 |
| 1.88s | — | independent | aa | Jul 24, 2026 |
Includes index data from Artificial Analysis.
Providers
Live operational stats per hosting endpoint, via OpenRouter.
| Provider | Quant | Context | $/1M in · out | Uptime 24h | Latency | Throughput |
|---|---|---|---|---|---|---|
| Amazon Bedrock | — | 200K | $5 · $25 | 99.87% | — | — |
| Amazon Bedrock | — | 200K | $5.5 · $27.5 | 100.00% | — | — |
| Anthropic | — | 200K | $5 · $25 | 97.84% | — | — |
| Anthropic | — | 200K | $5 · $25 | 90.32% | — | — |
| Azure | — | 200K | $5 · $25 | — | — | — |
| — | 200K | $5 · $25 | 99.60% | — | — |