Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Gemini 2.5 Pro Google | GPT-5.3 Codex OpenAI |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2025-06-05 | 2026-02-05 |
| Context Window | 1049K | 400K |
| Max Output | 66K | 128K |
| Input Price (/1M) | $1.25 | $1.75 |
| Output Price (/1M) | $10 | $14 |
| Arena Elo | 1,450 | 1,480 |
| MMLU | 89% | 93% |
| GPQA | 74% | 81% |
| MATH | 90.2% | 96% |
| HumanEval | 93.2% | 93% |
| SWE-bench | 63.8% | 80% |
| AIME | 75% | 94% |
| SimpleQA | 41.5% | 58% |
| Capabilities | vision, tool-use, code, reasoning, audio | vision, tool-use, code, reasoning, agentic |