Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Claude Opus 4.5 Anthropic | Gemini 2.5 Flash Google |
|---|---|---|
| Tier | frontier | mid |
| Release Date | 2025-11-01 | 2025-06-17 |
| Context Window | 200K | 1049K |
| Max Output | 64K | 66K |
| Input Price (/1M) | $5 | $0.3 |
| Output Price (/1M) | $25 | $2.5 |
| Arena Elo | 1,467 | 1,410 |
| MMLU | 90.5% | 83.5% |
| GPQA | 87% | 65.8% |
| MATH | 92% | 82.1% |
| HumanEval | 96% | 90.3% |
| SWE-bench | 64% | — |
| AIME | 72% | 58% |
| SimpleQA | 36% | 28.3% |
| Capabilities | vision, tool-use, code, extended-thinking, agentic | vision, tool-use, code, reasoning, audio |