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

Benchmarks · coding

WeirdML v2

17 ML tasks where models write Python pipelines from scratch (shape inference, chess winners, Kolmogorov shuffles); mean accuracy across tasks.

111 models · 127 results · data as of 2026-11-06 · htihle.github.io ↗

Leaderboard

Chart settings
111 of 111 selected
GPT-6 Astra Pro xhigh

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.

Chart settings
111 of 111 selected

Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 87 more models under All models in settings.

All results

127 rows
#ModelEffortWeirdML v2Subscription $ / taskAPI $ / task
1GPT-6 Astra Proxhigh93.6%$29$29
2GPT-6 Astraxhigh93.3%$0.33$7.75
3Fable 5.1xhigh92.9%$1.82$12
4GPT-6 Astrahigh92.9%$0.13$2.98
5Fable 5.1high92.3%$0.50$3.20
6Fable 5xhigh91.9%$0.95$8.42
7Opus 5xhigh91.8%$0.082$4.74
8Opus 5high91.6%$0.038$2.19
9GPT-5.6 Sol Proxhigh89.4%$3.87$3.87
10GPT-5.6 Solmax88.8%$0.035$1.25
11Fable 5max87.8%$0.35$3.11
12GPT-5.6 Solxhigh87.0%$0.064$2.31
13Opus 5max86.3%$0.025$1.42
14GPT-5.5xhigh84.9%$0.071$2.57
15Gemini 3.8 Flashmax84.8%$0.021$0.51
16Opus 4.8xhigh82.9%$0.041$2.35
17Kimi K3max82.6%$0.19$2.05
18GPT-5.6 Terramax78.3%$0.007$0.25
19Opus 4.6max77.9%$5.78$5.78
20GPT-5.3 Codexxhigh77.9%$2.45$2.45
21GPT-5.4xhigh77.7%$5.72$5.72
22Opus 4.7max76.4%$1.82$1.82
23Opus 4.8medium76.0%$0.015$0.85
24Opus 4.7xhigh75.4%$7.95$7.95
25GLM 5.3max75.4%$0.056$0.54
26Qwen 3.8xhigh75.2%$1.42$1.42
27GPT-5.2xhigh72.2%$2.05$2.05
28Gemini 3.1 Prohigh72.1%$1.36$1.36
29Opus 4.8max70.5%$0.008$0.48
30GLM 5.2xhigh70.1%$0.015$0.51