Views
No views yet
| Tasks | Version | Filter | n-shot | Metric | Baseline | MXFP4A16 | NVFP4A16 | |||
|---|---|---|---|---|---|---|---|---|---|---|
| leaderboard_math_hard | none | exact_match | ↑ | 0.5521 | 0.4992 | 0.5234 | ||||
| - leaderboard_math_algebra_hard | 3 | none | 4 | exact_match | ↑ | 0.7655 | 0.7492 | 0.7818 | ||
| none | 4 | exact_match_original | ↑ | 0.6515 | 0.6221 | 0.5798 | ||||
| - leaderboard_math_counting_and_prob_hard | 3 | none | 4 | exact_match | ↑ | 0.5772 | 0.4309 | 0.4715 | ||
| none | 4 | exact_match_original | ↑ | 0.4146 | 0.3089 | 0.3089 | ||||
| - leaderboard_math_geometry_hard | 3 | none | 4 | exact_match | ↑ | 0.3864 | 0.3258 | 0.3788 | ||
| none | 4 | exact_match_original | ↑ | 0.3258 | 0.1818 | 0.2652 | ||||
| - leaderboard_math_intermediate_algebra_hard | 3 | none | 4 | exact_match | ↑ | 0.3357 | 0.2750 | 0.2714 | ||
| none | 4 | exact_match_original | ↑ | 0.2857 | 0.2179 | 0.1821 | ||||
| - leaderboard_math_num_theory_hard | 3 | none | 4 | exact_match | ↑ | 0.5909 | 0.5649 | 0.6039 | ||
| none | 4 | exact_match_original | ↑ | 0.4935 | 0.4221 | 0.3312 | ||||
| - leaderboard_math_prealgebra_hard | 3 | none | 4 | exact_match | ↑ | 0.7720 | 0.7202 | 0.7513 | ||
| none | 4 | exact_match_original | ↑ | 0.5596 | 0.4819 | 0.4508 | ||||
| - leaderboard_math_precalculus_hard | 3 | none | 4 | exact_match | ↑ | 0.2963 | 0.2370 | 0.2296 | ||
| none | 4 | exact_match_original | ↑ | 0.2519 | 0.1778 | 0.1704 |