HARE - BEAVER Origin - MEM-SQL: leaderboard

HARErequests partitionedbyhistoricalsourcebenchmark, NOT originalSpider/BIRDtestset. MEMusesOSL, othermethodsUSL; nativeTable5, all6modelcolumns. Modelandmethodretainedseparately. Metric: Execution accuracy (%). Source: https://arxiv.org/html/2611.18338v1

Metric: Execution accuracy (%). Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemini 4 Argon50.4#14
2GLM-5.3 Flash44.4#136
3Qwen 3.8 27B40#219
4GPT-6 Luna40#105
5Granite 4.2 8B37.3#1561
6Qwen 3.5 9B27.4#822

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=hare-beaver-origin-mem-sql · How It Works · Data refreshed daily, snapshot 2026-11-17.