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 · Professional work · Agents & computer use

Excel Modeling Benchmark v1.1

Agents build financial models in Excel. Share of tasks done correctly. Version 1.1, the one inside the Vals Index; its own page still shows version 1. From Vals AI.

29 models · 29 results · updated 2026-11-11 · vals.ai ↗

Leaderboard

Chart settings
29 of 29 selected
Fable 5.2 high

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
29 of 29 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. 14 more models under All models in settings.

More from this benchmark

1 published measures

All results

29 rows
#ModelEffortScoreSubscription $ / taskAPI $ / taskTime
1Fable 5.2high77.4%$0.25$6.6716 min
2Gemini 4 Carbonhigh76.5%$4.10$5.7627 min
3Sonnet 5.5max75.9%$0.099$6.5337 min
4Opus 5.5max75.8%$0.14$9.3335 min
5Gemini 4 Hydrogenxhigh75.8%$2.26$3.1711 min
6Gemini 4 Argonhigh74.8%$8.41$1238 min
7GPT-6.1 Terramax73.3%$0.021$0.5613 min
8Gemini 3.8 Flashhigh72.9%$0.33$8.2413 min
9GPT-6 Astramax72.7%$0.25$5.8313 min
10Muse Embermax72.2%$0.091$0.0914.8 min
11Grok 4.7xhigh71.5%$0.60$6.4835 min
12Kimi K3max71.3%$0.28$3.0712 min
13GPT-6.1 Solmax71.1%$0.038$1.1418 min
14GPT-6 Lunamax70.0%$0.010$0.1417 min
15Step 5 Previewhigh69.6%$1.33$1.3344 min
16Inkling 2 Smallmax69.5%free$0.5314 min
17DeepSeek V4.1 Flash 1017max69.2%free$0.3333 min
18GLM 5.3max69.1%$0.39$3.7936 min
19Hy4 previewhigh68.9%$0.59$0.7931 min
20MiMo V2.6 Flashhigh68.9%free$0.1125 min
21MiMo V2.6 Promax67.3%$0.28$0.3355 min
22GLM 5.3 Flashmax66.3%free$1.431.2 h
23Hy4max66.2%$0.18$0.6218 min
24Haiku 5.5max65.5%$0.029$1.3620 min
25DeepSeek V4 Pro 0813max65.1%$1.08$1.0837 min
26Muse Spark Openxhigh62.0%$5.35$5.351.4 h
27Mercury 3high57.9%$0.19$0.198.9 min
28Inklingmax41.0%$0.15$1.6726 min
29Inkling Smallmax40.8%$0.20$0.2520 min