← All models
Compare

Gemma 4 31B IT vs Grok 4.5

Gemma 4 31B IT (Google DeepMind) and Grok 4.5 (xAI) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeGemma 4 31B ITGoogle DeepMindGrok 4.5xAI · 2 in the news
Scores
Intelligence (ECI)142154
Coding3491
Math85
Reasoning & Knowledge2670
Agentic & Tools75
Specifications
DeveloperGoogle DeepMindxAI
FamilyGemmaGrok
ReleasedApr 2, 2026Jul 8, 2026
Parameters
AvailabilityOpen weights (restricted use)API access
Context window262K500K
Price — $/M input$0.10$2.00
Price — $/M output$0.35$6.00
Inputsimage, text, videotext, image, file
Outputstexttext
Benchmarks
SimpleQA Verified10%54%
WebDev Arena13801551
WeirdML52%46%
AIME 2024/202598%
APEX34%
ARC-AGI87%
ARC-AGI-253%
GPQA Diamond93%
Humanity's Last Exam40%
SciCode54%
SimpleBench70%

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 4.5?

On Epoch AI's Capabilities Index, Grok 4.5 scores higher (154) than Gemma 4 31B IT (142). 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 4.5?

Gemma 4 31B IT is cheaper on input tokens at $0.10 per million, versus $2.00 (representative OpenRouter pricing).

Which has a larger context window, Gemma 4 31B IT or Grok 4.5?

Grok 4.5 supports up to 500K tokens, compared with 262K for the other.

Which is better for coding, Gemma 4 31B IT or Grok 4.5?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.5 ranks higher — 91th vs 34th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.