Anthropic: Claude Sonnet 4.5
anthropic/claude-sonnet-4.5
Context: 1,000,000In: $3.00/1MOut: $15.00/1MUpdated 2026-08-05
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
Intelligence
36.4
Coding
52.1
Agentic
24.6
Metric profile
Trend over time
Intelligence
36.4
Coding
52.1
Agentic
24.6
Only 1 snapshot so far (data refreshes daily) — the trend line appears after the 2nd snapshot.
Classic evals (curated from model cards)
Anthropic Claude — manually maintained, may lag releases
MMLU-Pro
74%
GPQA Diamond
70.8%
HumanEval
92%
Design Arena (ELO by category)
| Category | ELO | Win rate | Rank |
|---|---|---|---|
| asciiart | 1244 | 56.4% | #13 |
| 3d | 1213 | 51.2% | #42 |
| website | 1213 | 52.1% | #47 |
| codecategories | 1212 | 51.7% | #43 |
| gamedev | 1211 | 51.3% | #43 |
| uicomponent | 1209 | 49.8% | #43 |
| mobileapps | 1196 | 52.3% | #18 |
| dataviz | 1193 | 47.4% | #51 |
| svg | 1162 | 52.2% | #42 |
| webapps | 1112 | 43.1% | #27 |
| fullstack | 1096 | 43.5% | #22 |