Gemini 3.1 Pro vs Qwen 3.6 Max (Preview)
Gemini 3.1 Pro (Google DeepMind) and Qwen 3.6 Max (Preview) (Alibaba) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.1 Pro leads on overall intelligence (ECI 155 vs 150).
- Qwen 3.6 Max (Preview) ranks higher for coding (66th vs 65th percentile).
| Attribute | Gemini 3.1 Pro | Qwen 3.6 Max (Preview) |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | 150 |
| Coding | 65 | 66 |
| Math | 74 | 42 |
| Reasoning & Knowledge | 94 | 70 |
| Agentic & Tools | 83 | 88 |
| Specifications | ||
| Developer | Google DeepMind | Alibaba |
| Family | Gemini | Qwen |
| Released | Feb 19, 2026 | Apr 20, 2026 |
| Parameters | — | — |
| Availability | API access | — |
| Context window | — | 262K |
| Price — $/M input | — | $1.04 |
| Price — $/M output | — | $6.24 |
| Inputs | — | text |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 96% | 91% |
| APEX | 34% | — |
| ARC-AGI | 98% | — |
| ARC-AGI-2 | 77% | — |
| FrontierMath | 37% | 23% |
| FrontierMath Tier 4 | 17% | 4% |
| GPQA Diamond | 94% | 89% |
| GSO (code optimization) | 23% | — |
| Humanity's Last Exam | 46% | 29% |
| METR task horizon | 6.4 h | — |
| SimpleBench | 80% | 63% |
| SimpleQA Verified | 77% | 57% |
| SWE-bench Verified | 76% | 77% |
| Terminal-Bench | 80% | — |
| WebDev Arena | 1461 | 1486 |
| WeirdML | 72% | — |
| SciCode | — | 47% |
| τ²-bench | — | 96% |
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 Qwen 3.6 Max (Preview)?
On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than Qwen 3.6 Max (Preview) (150). 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 Qwen 3.6 Max (Preview)?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Qwen 3.6 Max (Preview) ranks higher — 66th vs 65th 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.