Claude model for long-running agentic coding and knowledge work
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 57.6 | — | independent | aa | Sep 22, 2026 |
| 57.6 | — | mirror | openrouter | Sep 23, 2026 | ||
| Design Arena — 3d | preference | 1480 | — | mirror | openrouter | Oct 16, 2026 |
| 1478 | — | mirror | openrouter | Oct 17, 2026 | ||
| 1477 | — | mirror | openrouter | Oct 20, 2026 | ||
| Design Arena — codecategories | preference | 1391 | — | mirror | openrouter | Oct 16, 2026 |
| 1390 | — | mirror | openrouter | Oct 20, 2026 | ||
| Design Arena — dataviz | preference | 1399 | — | mirror | openrouter | Oct 17, 2026 |
| 1397 | — | mirror | openrouter | Oct 20, 2026 | ||
| Design Arena — gamedev | preference | 1460 | — | mirror | openrouter | Oct 16, 2026 |
| 1461 | — | mirror | openrouter | Oct 16, 2026 | ||
| 1463 | — | mirror | openrouter | Oct 17, 2026 | ||
| 1457 | — | mirror | openrouter | Oct 20, 2026 | ||
| Design Arena — mobileapps | preference | 1322 | — | mirror | openrouter | Oct 20, 2026 |
| Design Arena — svg | preference | 1332 | — | mirror | openrouter | Oct 17, 2026 |
| 1332 | — | mirror | openrouter | Oct 19, 2026 | ||
| Design Arena — uicomponent | preference | 1378 | — | mirror | openrouter | Oct 16, 2026 |
| 1380 | — | mirror | openrouter | Oct 17, 2026 | ||
| 1384 | — | mirror | openrouter | Oct 20, 2026 | ||
| Design Arena — webapps | preference | 1318 | — | mirror | openrouter | Oct 20, 2026 |
| Design Arena — website | preference | 1338 | — | mirror | openrouter | Oct 16, 2026 |
| 1336 | — | mirror | openrouter | Oct 16, 2026 | ||
| 1336 | — | mirror | openrouter | Oct 20, 2026 | ||
| LMArena Text | preference | 1516 | high-effort | crowd | lmarena | Oct 13, 2026 |
| LMArena Vision | preference | 1321 | high-effort | crowd | lmarena | Oct 9, 2026 |
| Median output speed | speed | 95 tok/s | — | independent | aa | Oct 19, 2026 |
| Median time to first token | speed | 551.12s | — | independent | aa | Oct 20, 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 | — | 1M | $4 · $20 | 100.00% | — | — |
| Amazon Bedrock | — | 1M | $4.4 · $22 | 100.00% | — | — |
| Amazon Bedrock | — | 1M | $4.4 · $22 | 100.00% | — | — |
| Anthropic | — | 1M | $4 · $20 | 100.00% | — | — |
| Anthropic | — | 1M | $8 · $40 | 99.75% | — | — |
| Azure | — | 1M | $4 · $20 | 100.00% | — | — |
| Azure | — | 1M | $4.4 · $22 | — | — | — |
| Claude Platform on AWS | — | 1M | $4 · $20 | 100.00% | — | — |
| — | 1M | $4.4 · $22 | 100.00% | — | — | |
| — | 1M | $4 · $20 | 100.00% | — | — | |
| — | 1M | $4.4 · $22 | 100.00% | — | — |