Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theorem Proving on ProverBench
Loading...
5.5
Proof Length
Claude 4.6 Opus
3.028
19.714
36.4
53.086
Apr 29, 2026
Proof Length
Updated 1mo ago
Evaluation Results
Method
Method
Links
Proof Length
Claude 4.6 Opus
Type=Proprietary LLM
2026.04
5.5
Gemini 3.1 Pro
Type=Proprietary LLM
2026.04
6.6
Gemini 2.5 Pro
Type=Proprietary LLM
2026.04
12.7
GPT-5.3-Codex
Type=Proprietary LLM
2026.04
12.8
DeepSeek-Prover-V2-7B
Type=Open-source LLM
2026.04
19.6
Goedel-Prover-V2-8B
Type=Open-source LLM
2026.04
21.7
DreamProver
Backbone=GPT-5.3-Codex...
2026.04
34.1
Goedel-Prover-V2-32B
Type=Open-source LLM
2026.04
41.8
DreamProver
Backbone=Gemini 2.5 Pr...
2026.04
41.8
Hilbert
Backbone=Gemini 2.5 Pr...
2026.04
45.8
DreamProver
Backbone=Gemini 3.1 Pr...
2026.04
51.7
Hilbert
Backbone=Gemini 3.1 Pr...
2026.04
65.7
Hilbert
Backbone=GPT-5.3-Codex...
2026.04
67.3
Feedback
Search any
task
Search any
task