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 · composite

AA Intelligence Index v5.0.1

Artificial Analysis' composite intelligence score (v5.0.1), combining 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1.

34 models · 81 results · data as of 2026-11-03 · artificialanalysis.ai ↗

Leaderboard

Chart settings
34 of 34 selected
Gemini 4 Carbon 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.

19 more in settings
Chart settings
34 of 34 selected

More from this benchmark

14 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Gemini 4 Carbon high7.765.30.0472.043.212.461.441.01
Opus 5.5 max10.06.570.03574.741.83.472.411.06
GPT-6 Astra max6.243.650.08152.171.392.61.790.811
GPT-6.1 Sol max1.270.5940.01630.2520.3260.6780.4920.186
Sonnet 5.5 max10.07.170.01784.882.272.852.060.79
GPT-6.1 Terra max0.9610.6620.008150.4260.2270.2990.1970.103
Gemini 4 Argon high7.685.360.02452.073.262.331.370.961
Fable 5.1 xhigh10.86.070.08753.062.924.782.752.03
Kimi K3.1 max3.682.960.01672.10.840.7220.4420.28
GPT-6 Sol max2.471.930.01631.50.4080.5390.3540.185
Muse Wonder (Max)6.955.030.02533.791.221.921.170.75
Muse Spark 1.3 max2.3920.007921.710.2770.3870.2320.156
Haiku 5.5 max0.4110.2980.0008880.2330.06460.1130.08640.0266
Grok 4.7 xhigh7.777.140.01174.572.570.6270.4170.211
DeepSeek V4.1 Flash 1017 max0.6020.4350.001150.1780.2560.1670.1090.058
GPT-5.6 Terra max3.732.940.01632.350.5710.7940.4940.3
GLM 5.3 max5.014.490.002484.130.3490.5240.3730.151
Gemini 3.8 Flash high7.777.390.00310.3647.030.3710.2250.146
MiMo V2.6 Pro0.2570.1520.0008280.04280.1080.1050.07510.0303
GPT-6 Luna max0.1520.1140.0008150.08960.02390.03760.02880.00887
GLM 5.3 Flash max0.5830.5160.001210.4760.03860.06710.05130.0158
MiMo V2.6 Flash0.1290.09160.0009390.04840.04220.03690.02790.00899
Mistral Large 4 high2.061.890.00450.7821.10.1720.1140.0576
Muse Spark Open xhigh2.021.740.007961.10.6320.2820.1370.145
DeepSeek V4 Pro 0813 max1.771.380.002290.9050.4710.3910.240.151

All results

81 rows
#ModelEffortScoreSubscription $ / taskAPI $ / taskOutput tokens
1Gemini 4 Carbonhigh60.0$2.76$7.76123k
2Opus 5.5max59.1$0.15$10173k
3Gemini 4 Carbonmedium58.3$2.35$6.59103k
4Opus 5.5xhigh57.4$0.092$6.05103k
5GPT-6 Astramax56.9$0.27$6.2452k
6GPT-6 Astraxhigh55.3$0.16$3.6627k
7GPT-6 Astrahigh54.8$0.14$3.2423k
8GPT-6.1 Solmax54.6$0.074$1.2768k
9Sonnet 5.5max54.5$0.15$10285k
10Gemini 4 Carbonlow54.2$2.56$7.1986k
11GPT-6.1 Solxhigh52.5$0.045$0.7630k
12Opus 5.5high51.8$0.052$3.4660k
13GPT-6 Astramedium51.6$0.12$2.7318k
14GPT-6.1 Terramax51.3$0.092$0.9660k
15Gemini 4 Argonhigh50.4$2.74$7.68116k
16GPT-6.1 Solhigh50.3$0.034$0.5923k
17Fable 5.1xhigh50.0$1.69$1197k
18Sonnet 5.5xhigh49.9$0.062$4.09122k
19Fable 5.1max49.2$2.03$13118k
20Opus 5.5medium48.2$0.037$2.4544k
21Fable 5.1high47.2$1.18$7.5466k
22Kimi K3.1max46.5$3.68$3.6872k
23GPT-6.1 Solmedium46.3$0.021$0.3614k
24GPT-6.1 Terraxhigh45.3$0.038$0.4026k
25GPT-6 Solmax44.1$0.076$2.4754k
26Muse Wonder (Max)max43.6$4.63$6.9596k
27GPT-6 Astralow43.3$0.061$1.429.1k
28Fable 5.1medium43.2$0.87$5.5649k
29GPT-6.1 Terrahigh42.4$0.025$0.2617k
30Sonnet 5.5high41.5$0.025$1.6458k