Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theorem-based Question Answering on TheoremQA
Loading...
86.32
Accuracy
Meta-reasoner
44.2624
55.1812
66.1
77.0188
Feb 27, 2025
Apr 21, 2025
Jun 14, 2025
Aug 7, 2025
Sep 29, 2025
Nov 22, 2025
Jan 15, 2026
Accuracy
Updated 26d ago
Evaluation Results
Method
Method
Links
Accuracy
Meta-reasoner
Model=gemini-exp-1206
2025.02
86.32
HiAR-ICL
Model=gemini-exp-1206
2025.02
84.41
Meta-reasoner
Model=gpt-4o-mini
2025.02
84.13
HiAR-ICL
Model=gpt-4o-mini
2025.02
83.48
Evo-Prompt
Model=gpt-4o-mini
2025.02
81.28
Evo-Prompt
Model=gemini-exp-1206
2025.02
80.32
Ministral-14B-Instruct-2512
2026.01
56.13
Qwen3-14B
Thinking=no-think
2026.01
55.88
LLaDA-2.0-Mini
Training=T3S
2026.01
51.5
Ling-Mini
2026.01
50.38
Qwen3-30B-A3B-Instruct-2507
2026.01
50.12
LLaDA-2.0-Mini
Training=SFT
2026.01
47
LLaDA-2.0-Mini
Training=Base
2026.01
45.88
Feedback
Search any
task
Search any
task