Tests explained · People's votes

People's votes on maths questions

People compared two anonymous answers to maths questions.

Run by

How to read it

A rating from thousands of head-to-head votes. Higher means people preferred its answers more often. The thin line is the likely range.

Used for

2 tasks on this site.

How the models did

Rating from blind votes · Higher is better

Gemini 3.8 Flash and Claude Fable 5.1 are neck and neck at the top, followed by Gemini 3.6 Flash and Kimi K3.

Gemini 3.8 Flash · Google DeepMind1st

Claude Fable 5.1 · Anthropic2nd

Gemini 3.6 Flash · Google DeepMind3rd

Kimi K3 · Moonshot AI4th

DeepSeek V4.1 Flash · DeepSeek5th

Gemini 3.1 Pro · Google DeepMind6th

GPT-5.6 Sol · OpenAI7th

Claude Sonnet 5 · Anthropic8th

GPT-6 Astra · OpenAI9th

GPT-5.6 Luna · OpenAI10th

DeepSeek V4 Pro · DeepSeek11th

Gemini 3.5 Flash-Lite · Google DeepMind12th

Claude Haiku 4.5 · Anthropic13th

Claude Opus 5.5 · AnthropicNot tested yet

GPT-6 Luna · OpenAINot tested yet

GPT-6 Sol · OpenAINot tested yet

Source: LMArena · votes as of 25 Sept 2026

Where we use it

Each task page labels this test by how closely it matches the task.

Task	How close
Best AI for studying and homework	Tests a related skill
Best AI for maths and science	Tests this task