FlinkEval v3.1 L0 - All Questions Judge Pass: leaderboard

FlinkEval tests natural-language requests for Flink SQL. Ground-truth-anchored correctness, face-value judgments and execution errors are separate metrics. The main comparison uses 666 questions; the specification-ladder study uses a matched 600-question cohort, with each information condition retained. This board reports adjudicated judge-pass rate (%). Higher is better.

Metric: Adjudicated judge-pass rate (%). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 579.6#20
2GPT-6 Astra79.3#6
3GPT-5.6 Sol70#30
4Gemini 3.6 Flash65#75
5GPT-OSS-120B35#703

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=flinkeval-v3-1-l0-all-questions-judge-pass · How It Works · Data refreshed daily, snapshot 2026-11-16.