ai.MODEST PRAISE. PUBLIC NUMBERS.

← Back to the scoreboard

ARC-AGI-2

Data as of 2026-10-14 / manually checked

4 models · 7 benchmarks · zero composite scores

pretty greatpretty okaynot yetTap a verdict for the number and source.

Solves unfamiliar visual grid puzzles from a few examples.

Why it matters

Tests adapting to a new rule.

How to read it

Percentage solved on the verified evaluation. Higher is better.

Run by ARC Prize. Last checked 2026-10-14.

Visit the benchmark source ↗

MODEL / VENDORARC-AGI-2abstract reasoning

OpenAI

GPT-5.2 Thinking

Pretty great at coding, abstract reasoning, science, math, long context.

pretty great

52.9%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14

OpenAI

GPT-5.1 Thinking

Pretty great at coding, science.

not yet

17.6%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14

Anthropic

Claude Opus 4.6

Pretty great at coding, terminal work.

ARC-AGI-2 not reported

Google

Gemini 4 Argon High

Pretty great at conversation.

ARC-AGI-2 not reported

The top score means the top sourced score in this snapshot. Different harnesses, budgets and samples can change results. A blank cell is a blank cell.