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 · Math · Behavior & style

BrokenArXiv 10/2026 (MathArena)

Plausible but false math statements taken from October 2026 arXiv papers. The model scores by saying the statement is false instead of "proving" it. From MathArena.

12 models · 12 results · data as of 2026-11-18 · matharena.ai ↗

Leaderboard

GPT-6.2 Astra max

Score vs subscription cost per task

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's most subsidized plan, or API price with no plan data. 4 more models under All models in settings.

All results

12 rows
#ModelEffortScoreSubscription $ / taskAPI $ / task
1GPT-6.2 Astramax93.8% ±6.3$0.16$2.43
2GPT-6.2 Solmax88.9% ±8.4$0.033$0.98
3Gemini 4 Carbonhigh82.7% ±10.1$1.10$18
4GPT-6.1 Solmax80.3% ±7.5$0.044$1.30
5Opus 5.5high77.8% ±7.8$0.042$3.26
6Fable 5.2max73.5% ±11.8$1.46$40
7Inkling 2 Smallmax63.3% ±9.1free$0.24
8Kimi K3.1max58.0% ±9.3$1.05$1.58
9DeepSeek V4.1 Flash 1017max49.7% ±9.4free$0.26
10Gemini 4 Argonhigh39.8% ±9.2$8.35$13
11Muse Spark Openxhigh33.3% ±8.9$0.32$0.32
12Mistral Large 4high30.6% ±8.7$0.039$0.83