Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Claude Sonnet 4.6 Anthropic | GPT-4.1 mini OpenAI |
|---|---|---|
| Tier | frontier | mid |
| Release Date | 2026-02-17 | 2025-04-14 |
| Context Window | 200K | 1048K |
| Max Output | 64K | 33K |
| Input Price (/1M) | $3 | $0.4 |
| Output Price (/1M) | $15 | $1.6 |
| Arena Elo | 1,470 | 1,280 |
| MMLU | 91% | 80.5% |
| GPQA | 88% | 52.1% |
| MATH | 97.8% | — |
| HumanEval | 96% | 89.5% |
| SWE-bench | 70.3% | — |
| Capabilities | vision, tool-use, code, extended-thinking | vision, tool-use, code |