Gemma 4 31B IT vs Grok 4.6
Gemma 4 31B IT (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 143).
- Gemma 4 31B IT is cheaper on input tokens — $0.12 vs $2.00 per 1M.
- Grok 4.6 has a larger context window (500K vs 262K tokens).
- Grok 4.6 ranks higher for coding (92th vs 26th percentile).
| Attribute | Gemma 4 31B IT | Grok 4.6 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 143 | 156 |
| Coding | 26 | 92 |
| Math | 14 | 91 |
| Reasoning & Knowledge | 18 | 73 |
| Agentic & Tools | — | 84 |
| Specifications | ||
| Developer | Google DeepMind | xAI |
| Family | Gemma | Grok |
| Released | Apr 2, 2026 | Aug 12, 2026 |
| Parameters | — | — |
| Availability | Open weights (restricted use) | API access |
| Context window | 262K | 500K |
| Price — $/M input | $0.12 | $2.00 |
| Price — $/M output | $0.35 | $6.00 |
| Inputs | image, text, video | text, image, file |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 73% | 99% |
| GPQA Diamond | 76% | 94% |
| SimpleQA Verified | 10% | 49% |
| WebDev Arena | 1364 | 1629 |
| WeirdML | 52% | 67% |
| APEX | — | 41% |
| ARC-AGI | — | 88% |
| ARC-AGI-2 | — | 67% |
| Humanity's Last Exam | — | 43% |
| SciCode | — | 56% |
| SimpleBench | — | 76% |
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 Gemma 4 31B IT better than Grok 4.6?
On Epoch AI's Capabilities Index, Grok 4.6 scores higher (156) than Gemma 4 31B IT (143). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Gemma 4 31B IT or Grok 4.6?
Gemma 4 31B IT is cheaper on input tokens at $0.12 per million, versus $2.00 (representative OpenRouter pricing).
Which has a larger context window, Gemma 4 31B IT or Grok 4.6?
Grok 4.6 supports up to 500K tokens, compared with 262K for the other.
Which is better for coding, Gemma 4 31B IT or Grok 4.6?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.6 ranks higher — 92th vs 26th 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.