Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Claude Haiku 4.5 Anthropic | Claude Sonnet 4.5 Anthropic |
|---|---|---|
| Tier | mid | frontier |
| Release Date | 2025-10-01 | 2025-09-29 |
| Context Window | 200K | 200K |
| Max Output | 64K | 64K |
| Input Price (/1M) | $1 | $3 |
| Output Price (/1M) | $5 | $15 |
| Arena Elo | 1,404 | 1,450 |
| MMLU | 82% | 88.7% |
| GPQA | 55% | 83.4% |
| MATH | — | 87% |
| HumanEval | 90% | 95% |
| SWE-bench | — | 55.8% |
| Capabilities | vision, tool-use, code, extended-thinking | vision, tool-use, code, extended-thinking |