Side-by-side comparison of AI model specs, benchmarks, and pricing.
| Spec | Gemini 3 Flash Google | GPT-5.3 Codex OpenAI |
|---|---|---|
| Tier | frontier | frontier |
| Release Date | 2025-12-17 | 2026-02-05 |
| Context Window | 1049K | 400K |
| Max Output | 66K | 128K |
| Input Price (/1M) | $0.5 | $1.75 |
| Output Price (/1M) | $3 | $14 |
| Arena Elo | 1,470 | 1,480 |
| MMLU | 88% | 93% |
| GPQA | 80% | 81% |
| MATH | 90% | 96% |
| HumanEval | 94% | 93% |
| SWE-bench | 57% | 80% |
| AIME | 72% | 94% |
| SimpleQA | 36% | 58% |
| Capabilities | vision, tool-use, code, reasoning, audio | vision, tool-use, code, reasoning, agentic |