OptionProbability
Inkling (or any Thinking Machines model)
Qwen 4 (or any Qwen model)
Gemini 4 Carbon
GPT-6.2 Astra (6.x counts)
Claude Fable 5.5 (5.2+ counts)
GLM-5.4 (or any GLM model)
GPT-6.2 Sol
Muse Wonder 1.x
Nemotron 4 (or any Nemotron model)
Any Nano Banana model
MiMo V2.7 / V3 (or any MiMo model)
Claude Opus 5.6
Grok 4.8 (or any Grok/Composer model)
GPT-6.2 Luna (6.x counts)
DeepSeek V4.1 Pro / V5 (or any DeepSeek model)
MiniMax M3.2 (or any MiniMax model)
Any Mistral model
Gemini 4 Flash-Lite
Muse Spark 1.x/2.x
Gemini 4 Flash
Claude Haiku 5.6
GPT-6.2 Terra
Kimi K3.2 / K4 (or any Kimi model)
Claude Sonnet 5.6
Beam 1.x (or any Reflection model)
Any Safe Superintelligence (SSI) model
100
96
93
89
87
81
80
78
71
65
63
62
57
53
48
40
39
33
32
31
24
18
17
6
OptionVotes
YES
NO
762
Before 2027-02-16
Before 2027-02-01
Before 2027-01-16
Before 2027-01-01
Before 2026-12-16
Before 2026-12-01
Before 2026-11-16
86
84
67
50
20
Gemini 4 Pro 5-8 points worse
Gemini 4 Pro 0-4 points worse
Gemini 4 Pro ≥9 points worse
Gemini 4 Pro scores higher than the prior leading model
91
3
2
268