live
weekly refresh
basedagi.org
benchmark evidence

EQ-Bench Judgemark

LLM-as-judge calibration benchmark measuring how well a model correlates with human raters when used as an evaluator. Score 0-100.

winner on EQ-Bench Judgemark
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1Mistral: Mistral Small 4
Mistralai
28.9
model-only
independent_benchmark
2000-01-01
what this result means

LLM-as-judge calibration benchmark measuring how well a model correlates with human raters when used as an evaluator. Score 0-100.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on EQ-Bench Judgemark. Broad task pages require independent corroboration before naming a general winner.

source record
category: eq
metric: accuracy
matched models: 1
latest source date: 2000-01-01
direction: higher is better
inspect upstream source ->