List your company

Logical Reasoning on RuleBERT

67.7AccuracyBeam Search
40.34847.44954.5561.651Apr 22, 2026

Evaluation results

MethodLinks
Beam SearchModel=Gemma-3-4b-it, beam size=52026.0467.7
Beam Search (BL)Model=Gemma-3-4b-it2026.0467.7
Self-ConsistencyModel=Gemma-3-4b-it, n=52026.0463.9
BranchingModel=Gemma-3-4b-it2026.0463.4
BranchingModel=Gemma-3-4b-it2026.0463.4
SteeringModel=Gemma-3-4b-it2026.0462
TTPOModel=Gemma-3-4b-it2026.0460.8
GreedyModel=Gemma-3-4b-it2026.0460.3
Greedy (BL)Model=Gemma-3-4b-it2026.0460.3
SteeringModel=Gemma-3-12b-it2026.0459
Greedy (BL)Model=Gemma-3-12b-it2026.0458.2
Beam Search (BL)Model=Gemma-3-12b-it2026.0457.5
TTPOModel=Gemma-3-12b-it2026.0457.3
BranchingModel=Gemma-3-12b-it2026.0457
BranchingModel=Phi-4-mini-instruct (4B)2026.0451.9
BranchingModel=Phi-4-mini-instruct (4B)2026.0451.9
Beam SearchModel=Phi-4-mini-instruct (4B), beam size=52026.0451.7
Beam Search (BL)Model=Phi-4-mini-instruct (4B)2026.0451.7
SteeringModel=Phi-4-mini-instruct (4B)2026.0450.8
TTPOModel=Phi-4-mini-instruct (4B)2026.0450.7
GreedyModel=Phi-4-mini-instruct (4B)2026.0450.3
Greedy (BL)Model=Phi-4-mini-instruct (4B)2026.0450.3
Self-ConsistencyModel=Phi-4-mini-instruct (4B), n=52026.0448.8
Beam Search (BL)Model=Phi-4-reasoning-plus (13B)2026.0447.4
TTPOModel=Phi-4-reasoning-plus (13B)2026.0443.7
BranchingModel=Phi-4-reasoning-plus (13B)2026.0443.2
Greedy (BL)Model=Phi-4-reasoning-plus (13B)2026.0441.6
SteeringModel=Phi-4-reasoning-plus (13B)2026.0441.4