Rankings

Leaderboard

Ranked by average peer-judged score · edge cases

Allmeta alignmentreasoningcodeanalysiscommunicationedge cases
#ModelProviderAvgWinsEvalsBar
1
Grok 4.1 Fast
edge cases: 7.78meta alignment: 7.90communication: 9.15
7.78110
2
GPT-5.2-Codex
edge cases: 7.76code: 7.92meta alignment: 8.34
7.76110
3
Claude Sonnet 4.5
edge cases: 7.73meta alignment: 8.56communication: 9.25
7.73210
4
Gemini 3 Flash Preview
edge cases: 7.72reasoning: 6.81meta alignment: 8.71
7.72110
5
Grok 3 (Direct)
meta alignment: 9.52reasoning: 6.56edge cases: 7.68
7.68110
6
MiMo-V2-Flash
meta alignment: 8.60analysis: 8.63communication: 8.75
7.61110
7
Claude Opus 4.5
code: 7.63reasoning: 7.01analysis: 8.44
7.60110
8
DeepSeek V3.2
reasoning: 6.54meta alignment: 8.45communication: 8.93
7.50110
9
GPT-OSS-120B
reasoning: 7.99code: 7.80meta alignment: 8.03
6.71110
10
Gemini 3 Pro Preview
code: 5.01edge cases: 6.67reasoning: 3.83
6.67010
10 models · peer-judged · self-judgments excluded