Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Grok 4.1 xAI | o3 OpenAI |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2025-11-17 | 2025-04-16 |
| Context Window | 2000K | 200K |
| Max Output | 16K | 100K |
| Input Price (/1M) | $0.2 | $2 |
| Output Price (/1M) | $0.5 | $8 |
| Arena Elo | 1,465 | 1,433 |
| MMLU | 90.2% | 89.4% |
| GPQA | 88% | 79.7% |
| MATH | — | 91.6% |
| HumanEval | 92% | 92.8% |
| SWE-bench | 65% | 71.7% |
| Capabilities | vision, tool-use, code, reasoning | vision, tool-use, code, reasoning |