Atlas

Benchmarks

Chartography (November 2026 rescoring)

Surge's Chartography board as rescored between its November 6 and November 18, 2026 site builds, on the 100 professional chart-reading tasks. The page has no changelog and names no metric, protocol, judge, tool access or run count. Surge's GitHub harness, unchanged since August 14, still describes ten no-tools runs per task judged by Gemini 3.5 Flash, while a Harbor-format release of the tasks, each a container holding the chart image, appeared on Hugging Face on November 10, and the launch post still says the best model reaches 45%. Kept apart from the original board because the runs it kept moved by as much as 59.9 points (Grok 4.7 xHigh, 14.7 to 74.6; Claude Opus 5.5 Max, 66.3 to 89.6).

Models
36
Top score
90.7
Leader
GPT-6.2 Astra
Updated
—
Resolution
~3 mo
Useful
Saturation
~Dec 2026
Projected
Signal
69thpercentile
141 benchmarks from 0.8 to 2.9196 benchmarks from 2.9 to 5.0131 benchmarks from 5.0 to 7.1105 benchmarks from 7.1 to 9.282 benchmarks from 9.2 to 11.365 benchmarks from 11.3 to 13.327 benchmarks from 13.3 to 15.421 benchmarks from 15.4 to 17.58 benchmarks from 17.5 to 19.68 benchmarks from 19.6 to 21.76 benchmarks from 21.7 to 23.84 benchmarks from 23.8 to 25.95 benchmarks from 25.9 to 28.03 benchmarks from 28.0 to 30.12 benchmarks from 30.1 to 32.14 benchmarks from 32.1 to 34.21 benchmark from 34.2 to 36.33 benchmarks from 36.3 to 38.41 benchmark from 38.4 to 40.52 benchmarks from 40.5 to 42.61 benchmark from 42.6 to 44.71 benchmark from 44.7 to 46.81 benchmark from 48.9 to 50.9

253rd strongest of 818

Signal-to-noise +9.03

Difficulty
60thpercentile
1 benchmark from 5.8 to 14.71 benchmark from 23.5 to 32.42 benchmarks from 32.4 to 41.21 benchmark from 41.2 to 50.12 benchmarks from 50.1 to 58.99 benchmarks from 58.9 to 67.88 benchmarks from 67.8 to 76.718 benchmarks from 76.7 to 85.523 benchmarks from 85.5 to 94.441 benchmarks from 94.4 to 103.232 benchmarks from 103.2 to 112.141 benchmarks from 112.1 to 121.049 benchmarks from 121.0 to 129.875 benchmarks from 129.8 to 138.760 benchmarks from 138.7 to 147.5122 benchmarks from 147.5 to 156.4135 benchmarks from 156.4 to 165.3124 benchmarks from 165.3 to 174.139 benchmarks from 174.1 to 183.021 benchmarks from 183.0 to 191.88 benchmarks from 191.8 to 200.72 benchmarks from 200.7 to 209.54 benchmarks from 209.5 to 218.4

329th hardest of 818

Capability needed 156.6

Organizations
36 dated models · 8 frontier modelsClosed weightsOpen weights
Data: Surge AIatlas.village.dev

Chartography (November 2026 rescoring) leaderboard

#ModelSettingScoreSource
1GPT-6.2 Astramax
90.7
2Claude Opus 5.5max
89.6
3GPT-6 Astramax
88.6
4GPT-6.2 Solmax
87.7
5Gemini 4 Hydrogenx-high
87.2
6Gemini 4 Neonhigh
86.6
7Gemini 4 Carbonhigh
85.5
8Muse Spark 1.3max
84.6
9Claude Opus 5max
84.4
10Gemini 3.8 Flashhigh
81.7
11Claude Fable 5.2max
80.8
12Claude Fable 5.1max
79.6
13GPT-6 Solmax
79.4
14Muse Embermax
79.3
15Claude Fable 5max
79.0
16GPT-5.6 Solmax
78.6
17Inkling 2 Small0.99
75.6
18Qwen4-Maxx-high
75.3
19Gemini 3.7 Flashhigh
74.9
20Grok 4.7x-high
74.6
21GLM-5.3 Flashmax
72.7
22GPT-5.6 Lunamax
72.2
23GPT-6 Lunamax
68.0
24Muse Spark 1.2x-high
66.7
25Kimi K3max
66.4
26GLM-5.3max
64.2
27Sonnet 5max
64.0
28GPT-5.6 Terrax-high
58.8
29Gemini 3.1 Pro Previewhigh
54.2
30Hy4high
49.2
31Grok 4.6x-high
44.4
32MiniMax M3.1 Flashmax
39.8
33Hy3high
20.3
34Muse Glimmer 30Bx-high
15.4
35Inklinghigh
15.0
36Mistral Large 3 675B Instruct 2512not supported
7.3

Related benchmarks

Loading Atlas data…