Gemini 3.1 Pro vs gpt-oss-120b
Gemini 3.1 Pro (Google DeepMind) and gpt-oss-120b (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.1 Pro leads on overall intelligence (ECI 155 vs 141).
- Gemini 3.1 Pro ranks higher for coding (65th vs 43th percentile).
| Attribute | Gemini 3.1 Pro | gpt-oss-120b |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | 141 |
| Coding | 65 | 43 |
| Math | 74 | 48 |
| Reasoning & Knowledge | 94 | 21 |
| Agentic & Tools | 83 | 10 |
| Specifications | ||
| Developer | Google DeepMind | OpenAI |
| Family | Gemini | GPT |
| Released | Feb 19, 2026 | Aug 5, 2025 |
| Parameters | — | 116.8B |
| Availability | API access | Open weights (unrestricted) |
| Context window | — | 131K |
| Price — $/M input | — | $0.04 |
| Price — $/M output | — | $0.17 |
| Inputs | — | text |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 96% | 89% |
| APEX | 34% | 5% |
| ARC-AGI | 98% | — |
| ARC-AGI-2 | 77% | — |
| FrontierMath | 37% | — |
| FrontierMath Tier 4 | 17% | — |
| GPQA Diamond | 94% | 76% |
| GSO (code optimization) | 23% | — |
| Humanity's Last Exam | 46% | 19% |
| METR task horizon | 6.4 h | 42 min |
| SimpleBench | 80% | 22% |
| SimpleQA Verified | 77% | 14% |
| SWE-bench Verified | 76% | — |
| Terminal-Bench | 80% | 19% |
| WebDev Arena | 1461 | — |
| WeirdML | 72% | 48% |
| LiveCodeBench | — | 88% |
| MMLU-Pro | — | 81% |
| SciCode | — | 39% |
| τ²-bench | — | 66% |
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
Is Gemini 3.1 Pro better than gpt-oss-120b?
On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than gpt-oss-120b (141). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is better for coding, Gemini 3.1 Pro or gpt-oss-120b?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Gemini 3.1 Pro ranks higher — 65th vs 43th 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.