Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Llama 4 Maverick Meta | Gemini 3.1 Pro Google |
|---|---|---|
| Tier | open | frontier |
| Release Date | 2025-04-05 | 2026-02-19 |
| Context Window | 1049K | 1049K |
| Max Output | 16K | 66K |
| Input Price (/1M) | $0.5 | $2 |
| Output Price (/1M) | $0.77 | $12 |
| Arena Elo | 1,365 | 1,500 |
| MMLU | 82.5% | 92.6% |
| GPQA | 69.8% | 94.3% |
| MATH | 75.8% | 96.8% |
| HumanEval | 91.5% | 94.6% |
| SWE-bench | — | 80.6% |
| AIME | 48% | 91.2% |
| SimpleQA | 27.5% | 79.6% |
| Capabilities | vision, tool-use, code | vision, tool-use, code, reasoning, agentic, audio |