Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Gemini 3 Flash Google | Grok 4.1 xAI |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2025-12-17 | 2025-11-17 |
| Context Window | 1049K | 2000K |
| Max Output | 66K | 16K |
| Input Price (/1M) | $0.5 | $0.2 |
| Output Price (/1M) | $3 | $0.5 |
| Arena Elo | 1,470 | 1,465 |
| MMLU | 88% | 90.2% |
| GPQA | 80% | 88% |
| MATH | 90% | — |
| HumanEval | 94% | 92% |
| SWE-bench | 57% | 65% |
| Capabilities | vision, tool-use, code, reasoning, audio | vision, tool-use, code, reasoning |