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 · agentic

Terminal-Bench 4.0 (Vals)

Vals AI's Terminal-Bench 4.0 aggregate scores from its external-runner leaderboard. Vals publishes a separate system set and score series from the tbench.ai harness-plus-model leaderboard, so the two sources remain distinct.

46 models · 47 results · updated 2026-11-05 · vals.ai ↗

Leaderboard

Chart settings
46 of 46 selected
Opus 5.5 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.

Chart settings
46 of 46 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. 32 more models under All models in settings.

More from this benchmark

1 published measures

All results

47 rows
#ModelEffortScoreSubscription $ / taskAPI $ / taskTime
1Opus 5.5max65.2%$0.20$131.1 h
2Sonnet 5.5max64.1%$0.25$171.4 h
3Gemini 4 Carbonhigh63.1%$2.66$7.4545 min
4GPT-6 Astramax59.6%$0.41$9.5836 min
5Fable 5.1max58.1%$2.68$171.0 h
6Gemini 4 Argonhigh57.6%$13$1854 min
7GPT-6.1 Solmax55.1%$0.10$1.7245 min
8Opus 5max53.5%$0.32$191.1 h
9GPT-6.1 Terramax49.5%$0.11$2.1634 min
10GPT-6 Solmax44.4%$0.18$5.7935 min
11Fable 5max41.4%$3.42$301.1 h
12Hy4high39.4%$0.37$1.2843 min
13GLM 5.3max38.9%$0.97$9.371.4 h
14GPT-5.6 Solmax37.9%$0.22$7.9834 min
15GLM 5.3 Flashmax37.4%free$1.221.0 h
16Haiku 5.5max36.4%$0.066$3.1252 min
17Qwen 3.8 Maxmax34.3%$1.26$112.5 h
18DeepSeek V4.1 Flash 1017max31.8%free$0.5441 min
19MiMo V2.6 Promax31.3%$0.38$0.462.7 h
20Grok 4.7xhigh28.8%$1.67$1850 min
21Muse Spark 1.3max24.7%$3.33$6.6553 min
22MiMo V2.6 Flashhigh24.2%free$0.212.4 h
23Opus 4.8max23.2%$0.30$171.2 h
24GPT-5.6 Terramax22.7%$0.15$5.6031 min
25DeepSeek V4.1 Flashhigh19.7%$0.036$0.5048 min
26Gemini 3.8 Flashhigh19.7%$0.35$8.651.8 h
27DeepSeek V4 Flash 0731high18.7%$0.77$0.771.8 h
28Grok 4.6high17.2%$0.52$5.0629 min
29Kimi K3max17.2%$1.13$123.2 h
30DeepSeek V4 Pro 0813max14.1%$3.31$3.311.5 h