Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on AIME 2026 (Avg@64)
Loading...
99.17
Avg@64
OpenAI GPT-5.4
87.4076
90.4613
93.515
96.5687
Jun 13, 2026
Avg@64
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@64
OpenAI GPT-5.4
2026.06
99.17
Gemini 3.1-Pro
2026.06
98.33
Claude Opus-4.6
2026.06
96.67
Claude Opus-4.7
2026.06
96.41
Kimi-K2.6
2026.06
96.4
DS-V4-Pro
2026.06
95.83
Ring-2.6-1T
variant=xhigh
2026.06
95.78
GLM-5.1
2026.06
95.3
Ring-2.6-1T
variant=high
2026.06
87.86
Feedback
Search any
task
Search any
task