List your company
ResearchFormerly WizWand

Pointwise evaluation on BIGGEN

0.584Spearman CorrHuman-crafted (existing) Rubrics
0.267840.349920.4320.51408May 28, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Human-crafted (existing) RubricsJudge Model=Claude Sonnet 4, Rubric Granularity=Instance-specific2026.050.5840.598
Human-crafted (existing) RubricsJudge Model=Qwen3 14B, Rubric Granularity=Instance-specific2026.050.5830.609
Human-crafted (existing) RubricsJudge Model=Llama 3.1 70B, Rubric Granularity=Instance-specific2026.050.5520.594
Annotation-free Preference Learning for Rubric GeneratorJudge Model=Claude Sonnet 4, Iteration=2, Generator Model=Qwen3 14B2026.050.510.521
Annotation-free Preference Learning for Rubric GeneratorJudge Model=Claude Sonnet 4, Iteration=1, Generator Model=Qwen3 14B2026.050.490.504
Training-free Rubric GenerationJudge Model=Claude Sonnet 4, Rubric Granularity=Instance-specific2026.050.4770.496
Training-free Rubric GenerationJudge Model=Claude Sonnet 4, Configuration=Highest Training-free2026.050.4770.496
Human-crafted (existing) RubricsJudge Model=Claude Sonnet 4, Rubric Granularity=Dataset-specific2026.050.4760.494
Training-free Rubric GenerationJudge Model=Claude Sonnet 4, Rubric Granularity=Dataset-specific2026.050.4610.453
DnA-EvalJudge Model=Claude Sonnet 4, Approach Type=Training-free Approach2026.050.4540.489
Training-free Rubric GenerationJudge Model=Qwen3 14B, Rubric Granularity=Instance-specific2026.050.4460.462
Training-free Rubric GenerationJudge Model=Qwen3 14B, Configuration=Highest Training-free2026.050.4460.462
Annotation-free Preference Learning for Rubric GeneratorJudge Model=Llama 3.1 70B, Iteration=2, Generator Model=Qwen3 14B2026.050.4450.452
Annotation-free Preference Learning for Rubric GeneratorJudge Model=Qwen3 14B, Iteration=2, Generator Model=Qwen3 14B2026.050.4410.461
Training-free Rubric GenerationJudge Model=Qwen3 14B, Rubric Granularity=Dataset-specific2026.050.440.455
Annotation-free Preference Learning for Rubric GeneratorJudge Model=Llama 3.1 70B, Iteration=1, Generator Model=Qwen3 14B2026.050.440.447
Annotation-free Preference Learning for Rubric GeneratorJudge Model=Qwen3 14B, Iteration=1, Generator Model=Qwen3 14B2026.050.4390.459
Human-crafted (existing) RubricsJudge Model=Qwen3 14B, Rubric Granularity=Dataset-specific2026.050.4360.45
DnA-EvalJudge Model=Qwen3 14B, Approach Type=Training-free Approach2026.050.4310.426
CheckEvalJudge Model=Claude Sonnet 4, Approach Type=Training-free Approach2026.050.4240.455
Training-free Rubric GenerationJudge Model=Llama 3.1 70B, Rubric Granularity=Instance-specific2026.050.420.434
Training-free Rubric GenerationJudge Model=Llama 3.1 70B, Configuration=Highest Training-free2026.050.420.434
Human-crafted (existing) RubricsJudge Model=Llama 3.1 70B, Rubric Granularity=Dataset-specific2026.050.3840.382
Training-free Rubric GenerationJudge Model=Llama 3.1 70B, Rubric Granularity=Dataset-specific2026.050.3780.361
Prometheus 8x7BApproach Type=Fine-tuned Model, Rubric Granularity=Instance-specific2026.050.3660.401
CheckEvalJudge Model=Qwen3 14B, Approach Type=Training-free Approach2026.050.3430.392
DnA-EvalJudge Model=Llama 3.1 70B, Approach Type=Training-free Approach2026.050.3370.353
RubricHubJudge Model=Qwen3 14B, Approach Type=Training-free Approach2026.050.3320.383
RubricHubJudge Model=Claude Sonnet 4, Approach Type=Training-free Approach2026.050.3250.336
CheckEvalJudge Model=Llama 3.1 70B, Approach Type=Training-free Approach2026.050.3180.361
RubricHubJudge Model=Llama 3.1 70B, Approach Type=Training-free Approach2026.050.3180.361
Prometheus 8x7BApproach Type=Fine-tuned Model, Rubric Granularity=Dataset-specific2026.050.280.307