Compare
Gemini 3.1 Pro vs Qwen3-235B-A22B (Jul 2025)
Gemini 3.1 Pro (Google DeepMind) and Qwen3-235B-A22B (Jul 2025) (Alibaba) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.1 Pro leads on overall intelligence (ECI 155 vs 145).
| Attribute | Gemini 3.1 Pro | Qwen3-235B-A22B (Jul 2025) |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | 145 |
| Coding | 65 | — |
| Math | 74 | 19 |
| Reasoning & Knowledge | 94 | 24 |
| Agentic & Tools | 83 | — |
| Specifications | ||
| Developer | Google DeepMind | Alibaba |
| Family | Gemini | Qwen |
| Released | Feb 19, 2026 | Sep 1, 2025 |
| Parameters | — | 235B |
| Availability | API access | Open weights (unrestricted) |
| Context window | — | — |
| Price — $/M input | — | — |
| Price — $/M output | — | — |
| Inputs | — | — |
| Outputs | — | — |
| Benchmarks | ||
| AIME 2024/2025 | 96% | 87% |
| APEX | 34% | — |
| ARC-AGI | 98% | 11% |
| ARC-AGI-2 | 77% | 1% |
| FrontierMath | 37% | 8% |
| FrontierMath Tier 4 | 17% | 0% |
| GPQA Diamond | 94% | 80% |
| GSO (code optimization) | 23% | — |
| Humanity's Last Exam | 46% | — |
| METR task horizon | 6.4 h | — |
| SimpleBench | 80% | — |
| SimpleQA Verified | 77% | 50% |
| SWE-bench Verified | 76% | — |
| Terminal-Bench | 80% | — |
| WebDev Arena | 1461 | — |
| WeirdML | 72% | 41% |
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 Qwen3-235B-A22B (Jul 2025)?
On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than Qwen3-235B-A22B (Jul 2025) (145). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
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.