Gemma 4 31B: benchmarks, price and rank
Gemma 4 31B from Google is 89th of 123 rated AI models on Spezia's leaderboard. It costs $0.09 in, $0.34 out per million tokens.
- 89th of 123 rated models
- Rating 904
- Rated on 9 benchmarks
- Open weights
- Released Apr 2, 2026
- 262,000 tokens of context
- Knows the world to January 2025
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 78th of 78 on SimpleQA Verified
- 95th of 103 on GPQA Diamond
- 80th of 94 on Epoch Capabilities Index
Price: $0.09 in, $0.34 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- Humanity's Last Exam26.5%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
44th of 74. The maker's own number, from Google, via LLM Stats.
- LiveCodeBench v680%
Programming contest problems collected after models were trained, from LeetCode, AtCoder and Codeforces.
21st of 43. The maker's own number, from Google, via LLM Stats.
- SimpleQA Verified10.4%
Short factual questions with one checked answer, asked without web search.
78th of 78. Independent result from Epoch AI.
- MMMU-Pro76.9%
College exam questions that need a picture to answer, such as charts, diagrams, maps and chemical structures, with more answer options than the original MMMU and some questions shown only as a screenshot.
24th of 51. The maker's own number, from Google, via LLM Stats.
- MRCR v2 (8 needles)66.4%
A very long conversation full of similar requests, where the model has to find and repeat particular earlier answers, eight of them at once.
8th of 24. The maker's own number, from Google, via LLM Stats.
- LMArena text1,443
People put a question to two anonymous models and vote for the better answer.
47th of 107. Independent result from LMArena.
- LMArena WebDev1,370
People ask two anonymous models to build the same web page or app and vote for the better one.
78th of 98. Independent result from LMArena.
- GPQA Diamond75.8%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
95th of 103. Independent result from Epoch AI.
- MMLU-Pro85.2%
Twelve thousand multiple-choice questions across fourteen subjects, from law and medicine to engineering, with ten options each.
16th of 56. The maker's own number, from Google, via LLM Stats.
- Epoch Capabilities Index144.3
One score built from dozens of benchmarks, set on a common scale so that models tested on different benchmarks can still be compared.
80th of 94. Independent result from Epoch AI.
1 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.