Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | GPT-5.1 OpenAI | Grok 4 xAI |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2025-11-13 | 2025-07-09 |
| Context Window | 400K | 256K |
| Max Output | 128K | 8K |
| Input Price (/1M) | $1.25 | $3 |
| Output Price (/1M) | $10 | $15 |
| Arena Elo | 1,458 | 1,410 |
| MMLU | 91.5% | 87.5% |
| GPQA | 88.1% | 87.5% |
| MATH | — | 91.7% |
| HumanEval | 96% | 90% |
| SWE-bench | 62% | 48% |
| Capabilities | vision, tool-use, code, reasoning, agentic | vision, tool-use, code, reasoning |