Compare
Gemini 3.1 Pro vs GPT-5.1-Codex
Gemini 3.1 Pro (Google DeepMind) and GPT-5.1-Codex (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.1 Pro ranks higher for coding (65th vs 51th percentile).
| Attribute | Gemini 3.1 Pro | GPT-5.1-Codex |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | — |
| Coding | 65 | 51 |
| Math | 74 | 77 |
| Reasoning & Knowledge | 94 | 60 |
| Agentic & Tools | 83 | 50 |
| Specifications | ||
| Developer | Google DeepMind | OpenAI |
| Family | Gemini | GPT |
| Released | Feb 19, 2026 | Nov 12, 2025 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | — | 400K |
| Price — $/M input | — | $1.25 |
| Price — $/M output | — | $10.00 |
| Inputs | — | text, image |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 96% | 96% |
| APEX | 34% | 21% |
| ARC-AGI | 98% | — |
| ARC-AGI-2 | 77% | — |
| FrontierMath | 37% | — |
| FrontierMath Tier 4 | 17% | — |
| GPQA Diamond | 94% | 86% |
| GSO (code optimization) | 23% | — |
| Humanity's Last Exam | 46% | 23% |
| METR task horizon | 6.4 h | — |
| SimpleBench | 80% | — |
| SimpleQA Verified | 77% | — |
| SWE-bench Verified | 76% | — |
| Terminal-Bench | 80% | 58% |
| WebDev Arena | 1461 | 1331 |
| WeirdML | 72% | — |
| LiveCodeBench | — | 85% |
| MMLU-Pro | — | 86% |
| SciCode | — | 40% |
| τ²-bench | — | 83% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is better for coding, Gemini 3.1 Pro or GPT-5.1-Codex?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Gemini 3.1 Pro ranks higher — 65th vs 51th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.