Our new X account is live! Follow @wizwand_team for updates

LLM-as-a-Judge on PandaLM Human Annotations (test)

0.7683Agreement

FairJudge-8B

Updated 4d ago

Evaluation Results

Method	Links
FairJudge-8B 2026.02		0.7683	0.7187	0.7254	0.7218
Qwen2.5-72B 2026.02		0.728	0.6625	0.636	0.6458
FairJudge-2B 2026.02		0.7153	0.6775	0.5999	0.6168
FlexVL 2026.02		0.7134	0.643	0.6218	0.63
Qwen3-VL-8B 2026.02		0.7005	0.6369	0.648	0.6379
GLM-4-9B 2026.02		0.7002	0.6986	0.5769	0.5955
FairJudge-4B 2026.02		0.6931	0.6465	0.6102	0.6218
JudgeLM 2026.02		0.6677	0.6383	0.7195	0.6392
InternVL3-14B 2026.02		0.6667	0.6507	0.6867	0.6227
PandaLM 2026.02		0.6582	0.4456	0.4893	0.4624
DeepSeek-V3-671B 2026.02		0.6476	0.5848	0.6113	0.5883
LLaVA-1.5-7B 2026.02		0.3713	0.4011	0.3924	0.2898
LLaVA-1.5-13B 2026.02		0.2989	0.4316	0.4167	0.2828