Gemma 4 26B-A4B: benchmarks, price and rank
Gemma 4 26B-A4B from Google is 102nd of 123 rated AI models on Spezia's leaderboard. It costs $0.07 in, $0.34 out per million tokens.
- 102nd of 123 rated models
- Rating 765
- Rated on 8 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
- 98th of 103 on GPQA Diamond
- 88th of 94 on Epoch Capabilities Index
- 81st of 98 on LMArena WebDev
Price: $0.07 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 Exam17.2%
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.
57th of 74. The maker's own number, from Google, via LLM Stats.
- LiveCodeBench v677.1%
Programming contest problems collected after models were trained, from LeetCode, AtCoder and Codeforces.
24th of 43. The maker's own number, from Google, via LLM Stats.
- MMMU-Pro73.8%
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.
35th of 51. The maker's own number, from Google, via LLM Stats.
- MRCR v2 (8 needles)44.1%
A very long conversation full of similar requests, where the model has to find and repeat particular earlier answers, eight of them at once.
12th of 24. The maker's own number, from Google, via LLM Stats.
- LMArena text1,434
People put a question to two anonymous models and vote for the better answer.
60th of 107. Independent result from LMArena.
- LMArena WebDev1,358
People ask two anonymous models to build the same web page or app and vote for the better one.
81st of 98. Independent result from LMArena.
- GPQA Diamond73.2%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
98th of 103. Independent result from Epoch AI.
- MMLU-Pro82.6%
Twelve thousand multiple-choice questions across fourteen subjects, from law and medicine to engineering, with ten options each.
29th of 56. The maker's own number, from Google, via LLM Stats.
- Epoch Capabilities Index141.6
One score built from dozens of benchmarks, set on a common scale so that models tested on different benchmarks can still be compared.
88th 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.