Gemma 4 31B Benchmark Details

Gemma 4 31B currently shows benchmark results led by MMLU Pro (25 / 133, score 85.20), LiveCodeBench (32 / 126, score 80), GPQA Diamond (93 / 226, score 84.30). This page also compares it with 3 competitor models and 2 predecessor or same-series models, including performance and pricing views when available. 1 source link is attached for reference.

Benchmark Results

Gemma 4 31B

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

MMLU Pro

Thinking Mode

85.20

25 / 133

LiveBench

Standard Mode

61.62

62 / 115

HLE

Thinking Mode

19.50

129 / 181

HLE

Thinking ModeToolsInternet

26.50

104 / 181

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Mode

84.30

93 / 226

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

CodeForces

Thinking Mode

2150

13 / 20

LiveCodeBench

Thinking Mode

32 / 126

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench

Thinking ModeTools

76.90

20 / 43

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

Thinking Mode

89.20

16 / 19

Multimodal Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

MathVision

Thinking Mode

85.60

7 / 10

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GDM-MRCR v2 (8-needle, 128K)

Thinking Mode

66.40

5 / 8

Compare with other models

Competitor Comparison

Benchmark scores for Gemma 4 31B compared against top models in its class

Gemma 4 31BGLM-5 Kimi K2.5 Qwen3.5-27B

Benchmark categories:

The chart shows each model’s highest score per benchmark within the current filter. Out-of-100 benchmarks use raw heights; out-of-range benchmarks are scaled within that benchmark while labels keep the original scores.

8 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.

Benchmark	Gemma 4 31BCurrent	GLM-5	Kimi K2.5	Qwen3.5-27B
HLE 综合评估	26.50Thinking Enabled ｜ Tools	50.40Thinking Enabled ｜ Tools	50.20Thinking Enabled ｜ Tools	48.50Thinking Enabled ｜ Tools
LiveBench 综合评估	61.62Standard Mode	68.85Standard Mode	69.07Thinking Enabled	--
MMLU Pro 综合评估	85.20Thinking Enabled	--	78.50Thinking Enabled	86.10Thinking Enabled
GPQA Diamond 科学与综合推理	84.30Thinking Enabled	86.00Thinking Enabled	87.60Thinking Enabled	85.50Thinking Enabled
CodeForces 编程与软件工程	2150.00Thinking Enabled	--	--	1899.00Thinking Enabled
LiveCodeBench 编程与软件工程	80.00Thinking Enabled	--	85.00Thinking Enabled	80.70Thinking Enabled ｜ Tools
τ²-Bench Agent能力评测	76.90Thinking Enabled ｜ Tools	89.70Thinking Enabled ｜ Tools	--	79.00Thinking Enabled ｜ Tools
AIME 2026 数学推理	89.20Thinking Enabled	92.70Thinking Enabled	92.50Thinking Enabled	--

Standard API Pricing: Gemma 4 31B vs. Peer Models

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
GLM-5	智谱AI	$1 / 1M tokens	$3.2 / 1M tokens	—
Kimi K2.5	Moonshot AI	$0.6 / 1M tokens	$3 / 1M tokens	—

Version History

How each version of the Gemma 4 31B series stacks up on benchmark tests

Gemma 4 31BGemma 3 - 27B (IT)Gemma2-27B

Benchmark categories:

3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.

Benchmark	Gemma 4 31BCurrent	Gemma 3 - 27B (IT)	Gemma2-27B
MMLU Pro 综合评估	85.20Thinking Enabled	67.50Standard Mode	56.54Standard Mode
GPQA Diamond 科学与综合推理	84.30Thinking Enabled	42.40Standard Mode	--
LiveCodeBench 编程与软件工程	80.00Thinking Enabled	29.70Standard Mode	--

Single-Benchmark Version Trend

Viewing: MMLU Pro · 综合评估

Benchmark

NormalNormal + ToolsThinkingThinking + ToolsDeepDeep + Tools

X-axis shows model and release date, Y-axis shows score; solid lines connect the same mode across versions, while dotted guides align modes within the same generation.

Standard API Pricing Across the Gemma 4 31B Series

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
Gemma 3 - 27B (IT)	DeepInfra	$0.09 / 1M tokens	$0.16 / 1M tokens	—

Sources

blog.googleblog.google