priors
Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Benchmarks · Vision · Reasoning & puzzles

Penalty Bench

Refereeing football penalties: 101 incidents from the 2026 season, judged penalty or no penalty against expert verdicts. Accuracy; the referee scored 47.5% on the pitch and 63.4% with VAR. A small, not-so-serious bench by Wenhao Chai.

9 models · 9 results · data as of 2026-11-13 · wenhaochai.com ↗

Leaderboard

Chart settings
9 of 9 selected
GPT-6.1 Terra

All results

9 rows
#ModelEffortPenalty BenchHarness
1GPT-6.1 Terra64.4% ±8.9Codex
2Gemini 4 Carbon63.4% ±9.4Antigravity
3GPT-6.1 Sol57.4% ±9.9Codex
4Opus 5.556.4% ±9.4Claude Code
5Gemini 4 Argon53.5% ±9.9Antigravity
6GPT-6 Luna52.5% ±9.9Codex
7Sonnet 5.546.5% ±9.9Claude Code
8Gemini 3.8 Flash44.6% ±9.9Antigravity
9Haiku 5.538.6% ±9.4Claude Code