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

AA-Briefcase v1.1

AA-Briefcase: agentic office-work tasks over real files (xlsx/pptx/docx/pdf) judged pairwise; reported as Elo.

105 models · 192 results · data as of 2026-11-06 · artificialanalysis.ai ↗

Leaderboard

Chart settings
105 of 105 selected
Sonnet 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
105 of 105 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. 27 more models under All models in settings.

More from this benchmark

43 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Sonnet 5.5 max1,8435,20216,79513,5059,0307,403
Opus 5.5 max1,2743,3089,0937,1445,2354,158
Kimi K3.1 max598.02,6115,7074,9524,0142,107
Fable 5.1 max625.02,0105,3025,3833,4302,209
Muse Wonder (Max)642.01,3744,8485,3834,632904.0
Opus 5 max937.02,2745,3495,3474,1001,978
Grok 4.7 xhigh634.01,6053,7354,6133,1551,766
Gemini 4 Carbon high448.02,3412,4883,0592,444406.0
Muse Spark 1.3 max509.01,6653,8694,6423,869471.0
Haiku 5.5 max1,2341,1538,0215,0023,9485,309
Qwen 3.8 Flash1,2781,88112,48213,58211,1254,223
DeepSeek V4.1 Flash 1017 max881.02,3936,9886,9715,6053,040
GPT-6 Astra max279.01,0582,3081,8531,568589.0
GPT-6.1 Sol max315.01,0682,5682,0691,859874.0
Grok 4.6 xhigh363.01,2842,3783,3462,021704.0
Fable 5 max, fallback643.01,9453,7263,7492,7021,445
Inkling 2 Small702.04,0965,6475,5964,9281,829
MiMo V2.6 Pro879.01,2395,4545,5924,3042,299
GLM 5.3 max984.007,2937,4215,5312,868
Kimi K3 max744.02,3114,9534,8793,5981,802
MiMo V2.6 Flash984.01,5745,2235,7494,3092,342
Gemini 4 Argon high423.01,9762,7124,3092,523218.0
GPT-5.6 Sol max677.01,0233,6972,9762,2981,347
GPT-6 Sol max492.01,1393,3072,9152,1191,088
GLM 5.3 Flash max1,0971,6317,3727,7696,1663,474

All results

192 rows
#ModelEffortAA-Briefcase v1.1Subscription $ / taskAPI $ / taskHarness
1Sonnet 5.5max1813 ±11$0.31$20Stirrup
2Opus 5.5max1800 ±11$0.32$21Stirrup
3Opus 5.5xhigh1760 ±11$0.19$12Stirrup
4Sonnet 5.5xhigh1742 ±12$0.11$6.98Stirrup
5Opus 5.5high1682 ±9$0.095$6.27Stirrup
6Kimi K3.1max1675 ±11$7.22$7.22Stirrup
7Fable 5.1max1669 ±8$3.54$23Stirrup
8Muse Wonder (Max)max1659 ±10$5.79$8.68Stirrup
9Opus 5max1655 ±8$0.31$18Stirrup
10Fable 5.1xhigh1649 ±8$2.77$18Stirrup
11Grok 4.7xhigh1637 ±9$0.74$8.03Stirrup
12Sonnet 5.5high1634 ±10$0.050$3.27Stirrup
13Grok 4.7high1629 ±9$0.59$6.38Stirrup
14Opus 5xhigh1629 ±8Stirrup
15Opus 5.5medium1620 ±9$0.067$4.40Stirrup
16Gemini 4 Carbonhigh1611 ±10$2.91$8.16Stirrup
17Gemini 4 Carbonmedium1602 ±11$2.52$7.06Stirrup
18Muse Spark 1.3max1581 ±9$1.64$3.28Stirrup
19Fable 5.1high1577 ±7$1.78$11Stirrup
20Haiku 5.5max1574 ±10$0.014$0.67Stirrup
21Qwen 3.8 Flash1574 ±8Stirrup
22DeepSeek V4.1 Flash 1017max1570 ±10free$0.68Stirrup
23GPT-6 Astramax1569 ±8$0.41$9.50Stirrup
24Gemini 4 Carbonlow1567 ±11$2.57$7.20Stirrup
25Opus 5high1557 ±7Stirrup
26GPT-6.1 Solmax1555 ±9$0.13$2.31Stirrup
27GPT-6 Astraxhigh1544 ±9$0.28$6.56Stirrup
28Grok 4.6xhigh1541 ±7$0.50$4.88Stirrup
29Fable 5max1535 ±7Stirrup
30Grok 4.6high1528 ±7Stirrup