BLEUBERI/eval/WildBench/leaderboard/data_dir
2025-06-04 20:36:43 +00:00
..
_create_tables.py initial commit 2025-06-04 20:36:43 +00:00
_merge_results.py initial commit 2025-06-04 20:36:43 +00:00
all_stat.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.-1.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.100.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.300.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.500.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.1000.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.1500.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.2000.json initial commit 2025-06-04 20:36:43 +00:00
all_stat_wildbench.3000.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-gpt4t-K=-1.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-gpt4t-K=500.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-gpt4t-K=1000.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-gpt4t-K=1500.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-haiku-K=-1.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-haiku-K=500.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-haiku-K=1000.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-haiku-K=1500.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-llama-K=-1.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-llama-K=500.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-llama-K=1000.json initial commit 2025-06-04 20:36:43 +00:00
pairwise-llama-K=1500.json initial commit 2025-06-04 20:36:43 +00:00
score-sonnet.json initial commit 2025-06-04 20:36:43 +00:00
score.json initial commit 2025-06-04 20:36:43 +00:00
wb_elo.txt initial commit 2025-06-04 20:36:43 +00:00
wb_elo_results.json initial commit 2025-06-04 20:36:43 +00:00