Gemini 3.1 Flash-Lite: benchmarks, price and rank
Gemini 3.1 Flash-Lite from Google is 97th of 123 rated AI models on Spezia's leaderboard. It costs $0.25 in, $1.50 out per million tokens.
- 97th of 123 rated models
- Rating 824
- Rated on 7 benchmarks
- Closed
- Released Mar 3, 2026
- 1 million 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
- 22nd of 23 on Finance Agent v2
- 91st of 98 on LMArena WebDev
- 66th of 76 on FrontierMath
Price: $0.25 in, $1.50 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 Exam8.6%
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.
Independent result from Epoch AI.
- FrontierMath27.7%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
66th of 76. Independent result from Epoch AI.
- MMMU-Pro76.8%
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.
26th of 51. The maker's own number, from Google, via LLM Stats.
- CharXiv Reasoning73.2%
Questions about real charts from scientific papers that need reasoning across the chart, not just reading off a value.
37th of 45. The maker's own number, from Google, via LLM Stats.
- MRCR v2 (8 needles)60.1%
A very long conversation full of similar requests, where the model has to find and repeat particular earlier answers, eight of them at once.
9th of 24. The maker's own number, from Google, via LLM Stats.
- LMArena text1,416
People put a question to two anonymous models and vote for the better answer.
73rd of 107. Independent result from LMArena.
- LMArena WebDev1,256
People ask two anonymous models to build the same web page or app and vote for the better one.
91st of 98. Independent result from LMArena.
- Finance Agent v230.0%
Real financial analysis work: finding figures in company filings and documents, multi-step calculations and written analysis.
22nd of 23. The maker's own number, from Google, via LLM Stats.
- Legal Agent Benchmark0%
Long, complex legal tasks graded against rubrics written by legal experts, covering facts, conclusions, citations and structure.
12th of 15. The maker's own number, from Google, via LLM Stats.
- GPQA Diamond81.8%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
87th of 103. Independent result from Epoch AI.
2 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.