Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Gemini 3.1 Pro Google | Claude Opus 4.6 Anthropic |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2026-02-19 | 2026-02-05 |
| Context Window | 1049K | 200K |
| Max Output | 66K | 128K |
| Input Price (/1M) | $2 | $5 |
| Output Price (/1M) | $12 | $25 |
| Arena Elo | 1,500 | 1,496 |
| MMLU | 92.6% | 92.5% |
| GPQA | 94.3% | 91.3% |
| MATH | 96.8% | 97.6% |
| HumanEval | 94.6% | 97% |
| SWE-bench | 80.6% | 72.5% |
| AIME | 91.2% | 83.3% |
| SimpleQA | 79.6% | 43.2% |
| Capabilities | vision, tool-use, code, reasoning, agentic, audio | vision, tool-use, code, extended-thinking, agentic |