Mathematical Reasoning on MATH 500 (pass@16)
90.49pass@16 Success RateS-trace-0.9
Evaluation Results
| Method | Links | |
|---|---|---|
| S-trace-0.9Backbone=Qwen3-8B2026.05 | 90.49 | |
| GRPO(λ)-0.9Backbone=Qwen3-8B2026.05 | 90.11 | |
| GRPOBackbone=Qwen3-8B2026.05 | 89.73 |
| Method | Links | |
|---|---|---|
| S-trace-0.9Backbone=Qwen3-8B2026.05 | 90.49 | |
| GRPO(λ)-0.9Backbone=Qwen3-8B2026.05 | 90.11 | |
| GRPOBackbone=Qwen3-8B2026.05 | 89.73 |