Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Context-aware Evaluation on VecEval (val)

78.61Lingo-Judge Accuracy

Gemini-2.5-Flash (Reference Baseline)

12.965230.007647.0564.0924Jun 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
78.6144.78
2026.06
55.9335.68
2026.06
55.6332.81
2026.06
54.4435.99
2026.06
52.2230.56
2026.06
26.0324.22
2026.06
22.2525.33
2026.06
18.2623.04
2026.06
15.4921.91