#261

Gemma 4 31B

Google Release: 2026-04-02 Tested on: 2026-10-01 02:32 google/gemma-4-31b-it::none

30.7BDenseOpen source

(medium) (none)

Summary

Gemma 4 31B scores 5.7 on AI BENCHY and ranks #261. It has 10.0 reliability, a 42.0% pass rate, $0.031 total cost, and 7.28s average response time.

What makes Gemma 4 31B unique: It stands out most in General Intelligence, where it ranks #1, while Tool Calling is its weakest area at #16.

Model facts

Researched on 2026-08-12

Reported

Parameters: 30.7B
Architecture: Dense
Availability: Open source
License: Apache-2.0

Parameter source Availability source

Score

5.7

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$0.031 ↓ -33.9%

Tested at: $0.047

Total Output Tokens

15,499

Total Input Tokens

270,970

Input Price

$0.090 / 1M

Output Price

$0.340 / 1M

Cache Read Price

$0.050 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 14

Attempt pass rate: 42.0%

Flaky tests

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

7.28s

Response Time (max): 44.73s

Response Time (total): 152.84s

Wrong answer: 11 API error: 2 Did not follow instructions: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#261 Gemma 4 31B

none

Cost: $0.001
Time: 12.8s
Tokens: 795 tok

Run history

Tested on	Score	Reliability	Total Cost	Compare
2026-10-01 02:32 Re-test	5.7	10.0	$0.031 ↓	Current run
2026-07-16 23:02 New test added	6.2	10.0	$0.035 ↑	Compare
2026-06-04 14:04 New test added	6.5	10.0	$0.004 ↓	Compare
2026-05-22 00:30 Suite changed	6.7	10.0	$0.003	Compare
2026-04-14 00:56 First recorded run	6.9	N/A	$0.003	Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

Run	Benchmark coverage	Score	Consistency	Reliability	Tests Correct	Flaky tests	Total Output Tokens	Total Input Tokens	Total Cost	Response Time (avg)
2026-10-01 02:32 · Current run	69/69 attempts	5.7	9.6	10.0	9/23	1	15,499	270,970	$0.031	7.28s
2026-07-16 23:02 · New test added	66/66 attempts	6.2	9.6	10.0	10/22	1	13,317	125,728	$0.035	5.34s
Difference	—	-0.5	0.0	0.0	-1	0	+2182	+145242	-$0.005	+1937ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date	Input Price	Output Price	Cache Read Price	Cache Write Price
2026-06-04 15:40	$0.120 / 1M	$0.370 / 1M	N/A	N/A
2026-06-05 23:32	$0.120 / 1M	$0.360 / 1M	N/A	N/A
2026-06-12 18:42	$0.120 / 1M	$0.350 / 1M	N/A	N/A
2026-07-14 10:48	$0.060 / 1M	$0.350 / 1M	N/A	N/A
2026-07-16 15:36	$0.220 / 1M	$0.550 / 1M	N/A	N/A
2026-07-25 03:22	$0.140 / 1M	$0.400 / 1M	N/A	N/A
2026-08-14 12:51	$0.100 / 1M	$0.340 / 1M	N/A	N/A
2026-10-01 18:33	$0.090 / 1M	$0.340 / 1M	$0.050 / 1M	N/A

Charts

Choose the first model, then click a second model to open a side-by-side page.

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category	Score	Consistency
Agentic	3.9	9.6
Anti-AI Tricks	6.5	10.0
Coding	5.5	10.0
Combined	3.8	5.8
Data parsing and extraction	10.0	10.0
Domain specific	5.3	10.0
General Intelligence	10.0	10.0
Instructions following	6.5	10.0
Puzzle Solving	6.5	10.0
Tool Calling	3.0	10.0
Trivia	3.0	10.0

Gemma 4 31B

Model facts

Hamster playing table tennis

#261 Gemma 4 31B

Charts

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Compared models