GPQA Diamond
?what it ishighest score on this metric 96.4%
102º / 198 · Epoch AI, latest version we checked
Gemma 4 31B
Benchmarks, price, context and versions
Also searched as
Gemma 4, Gemma, gemma 4 31b qat, gemma 4 31b benchmark, gemma 4 31b requirements
Direct answer: Gemma 4 31B is a model from Google. 75.8% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 0.20 per 1 million input tokens and US$ 0.40 per 1 million output tokens.
✓ Good for
- agents that follow rules and use tools (#29 of 131 on τ-bench Verified (airline))
- running on your own infrastructure (open weights)
✕ Not the best for
- technical reasoning on science topics (#102 of 198 on GPQA Diamond)
- calculation and problems with an exact answer (#95 of 186 on OTIS Mock AIME)
- answering short facts with little invention (#85 of 87 on SimpleQA Verified)
This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.
Benchmarks
OTIS Mock AIME
?highest score on this metric 100%
95º / 186 · Epoch AI, latest version we checked
SimpleQA Verified
?highest score on this metric 94%
85º / 87 · Epoch AI, latest version we checked
GPQA Diamond (OpenRouter)
?highest score on this metric 96.5%
64º / 135 · OpenRouter Benchmarks, latest version we checked
τ-bench Verified (airline)
?highest score on this metric 82%
29º / 131 · OpenRouter Benchmarks, latest version we checked
Key specs
Version history
- embeddinggemma-2 Hugging Face Hub, Hugging Face repo created
- diffusiongemma-26B-A4B-it Hugging Face Hub, Hugging Face repo created
- gemma-4-12B-it-assistant Hugging Face Hub, Hugging Face repo created
- gemma-4-12B-it Hugging Face Hub, Hugging Face repo created
- gemma-4-12B Hugging Face Hub, Hugging Face repo created
- gemma-4-31B-it-assistant Hugging Face Hub, Hugging Face repo created
- gemma-4-E4B-it-assistant Hugging Face Hub, Hugging Face repo created
- gemma-4-E2B-it-assistant Hugging Face Hub, Hugging Face repo created
- gemma-4-26B-A4B-it-assistant Hugging Face Hub, Hugging Face repo created
- Google: Gemma 4 26B A4B OpenRouter, listed on OpenRouter
- Google: Gemma 4 31B OpenRouter, listed on OpenRouter
- gemma-4-31B Hugging Face Hub, Hugging Face repo created
- gemma-4-26B-A4B Hugging Face Hub, Hugging Face repo created
- gemma-4-26B-A4B-it Hugging Face Hub, Hugging Face repo created
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.
FAQ
What is the context window of Gemma 4 31B?
262,144 tokens, per OpenRouter.
Is Gemma 4 31B open source?
Yes, it has open weights. License: no data.
What is Gemma 4 31B's GPQA Diamond score?
75.8% on GPQA Diamond, per Epoch AI.
What is Gemma 4 31B?
Gemma 4 31B is a model from Google, with open weights, used for text, agents.
How much does Gemma 4 31B cost?
On OpenRouter, US$ 0.20 per 1 million input tokens and US$ 0.40 per 1 million output tokens.
Is Gemma 4 31B good for coding?
No data: there is no SWE-bench Verified measurement for it in open sources.
Who made Gemma 4 31B?
It was made by Google, a lab from the US.
provisional data Questions ordered by what shows up in public Google search suggestions (no volume). Answers use source data only.
Compare with
Models from Google
Sources
- Epoch AI, CC BY 4.0, latest version we checked.
- OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
- OpenRouter Benchmarks, CC BY 4.0, latest version we checked.
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.