geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemma 4 31B IT

AI model Released

Context window
262,144 tokens
Maximum output
32,768 tokens
Open weights
Yes

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Gemma 4 31B IT 143.1* Gemma 4 31B IT · 95% interval 140.8–145.9

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Gemma 4 31B IT

Radar task score

Unrated

1/4 core tests · not enough evidence

1 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Gemma 4 31B IT Not available

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Gemma 4 31B IT Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Gemma 4 31B IT Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Gemma 4 31B IT 10.4*% Approx. 95% interval: 8.5–12.3%

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Run it locally

Inference · memory estimate

Gemma 4 31B IT

58.3 GiB checkpoint tensor payload · 31.27 B stored tensor elements · BF16

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Gemma 4 31B IT

Gemma 4 31B IT / Pricing tiers 2
Provider / scopeRateCurrencyAmount / unit
DeepInfragoogle/gemma-4-31B-itStandard InputUSD0.2 / 1M tokens
OutputUSD0.4 / 1M tokens
SambaNova Cloudgemma-4-31B-itStandard InputUSD0.38 / 1M tokens
OutputUSD1.15 / 1M tokens

Capabilities

Context window
262,144 tokens
Maximum output
32,768 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Knowledge cutoff
2025-01
Model license
apache-2.0
Checkpoint tensor payload
58.25 GiB

Input modalities

  • text
  • image

Output modalities

  • text

Processing & platform

Architecture
gemma4

* Provisional data