Mathematical Reasoning Benchmark
A standardized test set used to evaluate a model's mathematical reasoning ability, commonly used in knowledge distillation and reasoning capability evaluation.
Timeline (last 90 days)
D²-OPD achieves the highest scores under all three settings on math reasoning benchmarks, with an improvement of up to 9.45 points over the strongest baseline method.
L2RR was empirically evaluated on six mathematical reasoning benchmarks and three model scales, and the results show that L2RR improves target-domain performance while also improving rollout efficiency.
All Facts (2)
D²-OPD achieves the highest scores under all three settings on math reasoning benchmarks, with an improvement of up to 9.45 points over the strongest baseline method.
50%UnverifiedL2RR was empirically evaluated on six mathematical reasoning benchmarks and three model scales, and the results show that L2RR improves target-domain performance while also improving rollout efficiency.
50%