Math Reasoning on AIME 24 (Accuracy and Delta)
23.3AccuracyETO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ETOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=true2026.05 | 23.3 | 10 | |
| ED-iDPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=true2026.05 | 23.3 | 10 | |
| ED-GRPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=false2026.05 | 23.3 | 10 | |
| ED-GRPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=true2026.05 | 23.3 | 10 | |
| GRPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=true2026.05 | 20 | 6.7 | |
| CoTBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=true2026.05 | 16.7 | 3.4 | |
| ETOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=false2026.05 | 16.7 | 3.4 | |
| GRPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=false2026.05 | 16.7 | 3.4 | |
| DAPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=false2026.05 | 16.7 | 3.4 | |
| DAPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=true2026.05 | 16.7 | 3.4 | |
| ED-iDPOBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=false2026.05 | 16.7 | 3.4 | |
| CoTBase Model=Qwen2.5-7B-Instruct-SFT, Self-Consistency=false2026.05 | 13.3 | — | |
| ETOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=true2026.05 | 6.7 | 6.7 | |
| ED-iDPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=false2026.05 | 6.7 | 6.7 | |
| ED-iDPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=true2026.05 | 6.7 | 6.7 | |
| CoTBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=true2026.05 | 3.3 | 3.3 | |
| ETOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=false2026.05 | 3.3 | 3.3 | |
| GRPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=false2026.05 | 3.3 | 3.3 | |
| GRPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=true2026.05 | 3.3 | 3.3 | |
| DAPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=false2026.05 | 3.3 | 3.3 | |
| DAPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=true2026.05 | 3.3 | 3.3 | |
| ED-GRPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=false2026.05 | 3.3 | 3.3 | |
| ED-GRPOBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=true2026.05 | 3.3 | 3.3 | |
| CoTBase Model=LLaMA3.1-8B-Instruct-SFT, Self-Consistency=false2026.05 | 0 | — |