Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theorem Proving on MO-INT (Proof Length)
Loading...
17
Proof Length
Claude 4.6 Opus
12.376
43.588
74.8
106.012
Apr 29, 2026
Proof Length
Updated 1mo ago
Evaluation Results
Method
Method
Links
Proof Length
Claude 4.6 Opus
Type=Proprietary LLM
2026.04
17
Gemini 2.5 Pro
Type=Proprietary LLM
2026.04
35
DreamProver
Backbone=Gemini 2.5 Pr...
2026.04
45.3
Gemini 3.1 Pro
Type=Proprietary LLM
2026.04
47.9
DreamProver
Backbone=Gemini 3.1 Pr...
2026.04
50.6
DreamProver
Backbone=GPT-5.3-Codex...
2026.04
55.3
GPT-5.3-Codex
Type=Proprietary LLM
2026.04
60.5
DeepSeek-Prover-V2-7B
Type=Open-source LLM
2026.04
61.8
Goedel-Prover-V2-8B
Type=Open-source LLM
2026.04
76
Hilbert
Backbone=Gemini 2.5 Pr...
2026.04
93.4
Hilbert
Backbone=GPT-5.3-Codex...
2026.04
124.1
Goedel-Prover-V2-32B
Type=Open-source LLM
2026.04
128
Hilbert
Backbone=Gemini 3.1 Pr...
2026.04
132.6
Feedback
Search any
task
Search any
task