Gemini 3 Pro vs Grok 4.6
Gemini 3 Pro (Google DeepMind) and Grok 4.6 (xAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Grok 4.6 leads on overall intelligence (ECI 156 vs 153).
- Grok 4.6 ranks higher for coding (92th vs 43th percentile).
| Attribute | Gemini 3 Pro | Grok 4.6 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 153 | 156 |
| Coding | 43 | 92 |
| Math | 66 | 91 |
| Reasoning & Knowledge | 68 | 73 |
| Agentic & Tools | 49 | 84 |
| Specifications | ||
| Developer | Google DeepMind | xAI |
| Family | Gemini | Grok |
| Released | Nov 18, 2025 | Aug 12, 2026 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | — | 500K |
| Price — $/M input | — | $2.00 |
| Price — $/M output | — | $6.00 |
| Inputs | — | text, image, file |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 91% | 99% |
| APEX | 32% | 41% |
| ARC-AGI | 75% | 88% |
| ARC-AGI-2 | 31% | 67% |
| FrontierMath | 38% | — |
| FrontierMath Tier 4 | 19% | — |
| GDPval (win/tie rate) | 54% | — |
| GPQA Diamond | 93% | 94% |
| GSO (code optimization) | 19% | — |
| Humanity's Last Exam | 38% | 43% |
| METR task horizon | 3.7 h | — |
| SimpleBench | 76% | 76% |
| SimpleQA Verified | 73% | 49% |
| SWE-bench Verified | 73% | — |
| Terminal-Bench | 69% | — |
| WebDev Arena | 1438 | 1629 |
| WeirdML | 70% | 67% |
| SciCode | — | 56% |
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 Pro better than Grok 4.6?
On Epoch AI's Capabilities Index, Grok 4.6 scores higher (156) than Gemini 3 Pro (153). 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 Pro or Grok 4.6?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.6 ranks higher — 92th 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.