Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | GPT-5.1 OpenAI | GPT-5.3 Codex OpenAI |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2025-11-13 | 2026-02-05 |
| Context Window | 400K | 400K |
| Max Output | 128K | 128K |
| Input Price (/1M) | $1.25 | $1.75 |
| Output Price (/1M) | $10 | $14 |
| Arena Elo | 1,458 | 1,480 |
| MMLU | 91.5% | 93% |
| GPQA | 88.1% | 81% |
| MATH | — | 96% |
| HumanEval | 96% | 93% |
| SWE-bench | 62% | 80% |
| AIME | 82% | 94% |
| SimpleQA | 48% | 58% |
| Capabilities | vision, tool-use, code, reasoning, agentic | vision, tool-use, code, reasoning, agentic |