Spaces:

gujilab
/

chinese-classical-bench-leaderboard

Running

4.92 MB

Ctrl+K

sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity)

18d4517 verified 3 months ago

Qwen3.5-35B-A3B.json

398 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
claude-haiku-4-5-20251001.json

511 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
claude-opus-4-7-thinking.json

486 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
claude-opus-4-7.json

488 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
claude-sonnet-4-6.json

503 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
deepseek-3.2.json

494 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
glm-5.json

499 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
minimax-m2.1.json

537 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
minimax-m2.5.json

504 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago
qwen3-coder-next.json

496 kB
sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity) 3 months ago