Compare
DeepSeek-V4-Pro-0813 vs Gemini 3.1 Pro
DeepSeek-V4-Pro-0813 (DeepSeek) and Gemini 3.1 Pro (Google DeepMind) compared on benchmarks, pricing, context window, and use-case rankings.
- DeepSeek-V4-Pro-0813 ranks higher for coding (80th vs 59th percentile).
| Attribute | DeepSeek-V4-Pro-0813 | Gemini 3.1 Pro |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 155 |
| Coding | 80 | 59 |
| Math | 90 | 71 |
| Reasoning & Knowledge | 78 | 93 |
| Agentic & Tools | — | 79 |
| Specifications | ||
| Developer | DeepSeek | Google DeepMind |
| Family | DeepSeek | Gemini |
| Released | Aug 13, 2026 | Feb 19, 2026 |
| Parameters | 1.6T | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | 1M | — |
| Price — $/M input | $0.66 | — |
| Price — $/M output | $1.98 | — |
| Inputs | text | — |
| Outputs | text | — |
| Benchmarks | ||
| AIME 2024/2025 | 99% | 96% |
| GPQA Diamond | 92% | 94% |
| Humanity's Last Exam | 41% | 46% |
| SciCode | 49% | — |
| SimpleQA Verified | 55% | 77% |
| WebDev Arena | 1584 | 1461 |
| WeirdML | 66% | 72% |
| APEX | — | 34% |
| ARC-AGI | — | 98% |
| ARC-AGI-2 | — | 77% |
| FrontierMath | — | 37% |
| FrontierMath Tier 4 | — | 17% |
| GSO (code optimization) | — | 23% |
| METR task horizon | — | 6.4 h |
| SimpleBench | — | 80% |
| SWE-bench Verified | — | 76% |
| Terminal-Bench | — | 80% |
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, DeepSeek-V4-Pro-0813 or Gemini 3.1 Pro?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 80th vs 59th 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.