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 v4.3.2

Artificial Analysis' composite intelligence score (v4.3.2), combining 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, and AA-LCR v1.1.

195 models · 339 results · data as of 2026-11-06 · artificialanalysis.ai ↗

Leaderboard

Chart settings
195 of 195 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
195 of 195 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. 71 more models under All models in settings.

More from this benchmark

14 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Opus 5.5 max5.983.60.1032.421.072.381.680.705
Sonnet 5.5 max5.463.490.05152.211.231.971.470.508
Fable 5.1 max7.633.730.2591.61.863.92.361.54
GPT-6 Astra max3.261.90.2150.9810.7011.360.8350.526
Gemini 4 Argon high1.6210.080.3390.5860.6160.3550.26
Muse Wonder (Max)3.272.180.07121.510.5931.090.5760.514
GPT-6.1 Sol max0.7240.3430.0430.1230.1770.3810.2520.129
Opus 5 max5.864.050.1293.160.7611.811.070.743
Fable 5 max, fallback8.755.440.2533.861.323.312.231.08
GPT-6.1 Terra max0.4030.2280.02150.1140.09240.1750.1240.051
Muse Spark 1.3 max1.311.060.02250.8830.1540.2560.1450.111
GPT-6 Sol max1.040.7350.04280.5070.1850.310.2080.102
GPT-5.6 Sol max1.991.40.08610.990.3260.5860.3460.241
Grok 4.7 xhigh3.242.750.03281.71.020.4830.3510.132
MiMo V2.6 Pro0.1330.07730.004240.01950.05360.05590.03260.0233
DeepSeek V4.1 Flash 1017 max0.2620.1550.00390.05590.09480.1070.07110.0363
GLM 5.3 max2.011.690.01351.520.1570.3130.2140.0986
Grok 4.6 high1.481.270.03280.8980.3390.2150.1130.102
Kimi K3 max21.270.06620.8020.4050.7270.4870.24
Haiku 5.5 max0.2130.1320.002570.09540.03370.08110.06450.0166
GPT-5.6 Terra max1.40.9320.04540.660.2270.4670.3130.154
GLM 5.3 Flash max0.2840.2490.00330.2280.01840.03430.02330.011
Opus 4.8 max4.082.320.1281.60.5841.761.30.468
Ling 3.1 Flash1.010.9180.002980.5650.350.09260.06060.032
Gemini 3.8 Flash high3.493.220.01070.1573.050.2660.160.106

All results

339 rows
#ModelEffortScoreSubscription $ / taskAPI $ / taskOutput tokens
1Opus 5.5max57.6$0.091$5.98119k
2Sonnet 5.5max56.0$0.083$5.46197k
3Opus 5.5xhigh56.0$0.052$3.4666k
4Opus 5.5high53.6$0.028$1.8236k
5Fable 5.1max53.4$1.19$7.6378k
6Fable 5.1xhigh53.2$0.93$5.9861k
7GPT-6 Astramax52.7$0.14$3.2627k
8Gemini 4 Argonhigh52.6$1.15$1.6262k
9Muse Wonder (Max)max52.4$2.18$3.2754k
10GPT-6 Astraxhigh52.4$0.099$2.3117k
11Sonnet 5.5xhigh51.9$0.030$2.0175k
12GPT-6.1 Solmax51.8$0.042$0.7238k
13Opus 5.5medium51.2$0.020$1.3426k
14Fable 5.1high51.2$0.61$3.9138k
15GPT-6.1 Solxhigh51.0$0.023$0.3918k
16GPT-6 Astrahigh50.9$0.074$1.7312k
17Opus 5max50.8$0.10$5.8673k
18GPT-6.1 Solhigh50.2$0.019$0.3213k
19Opus 5xhigh49.7$0.085$4.8861k
20Fable 5max49.6$0.99$8.7567k
21GPT-6 Astramedium49.6$0.066$1.549.6k
22Fable 5.1medium48.9$0.46$2.9828k
23Opus 5high48.1$0.063$3.6146k
24GPT-6.1 Terramax48.1$0.020$0.4035k
25Muse Spark 1.3max48.1$0.66$1.3160k
26GPT-6.1 Solmedium47.8$0.012$0.218.1k
27GPT-6 Solmax47.6$0.032$1.0431k
28GPT-5.6 Solmax47.0$0.055$1.9929k
29Fable 5.1low46.8$0.37$2.3722k
30Sonnet 5.5high46.8$0.013$0.8837k