HARE - Spider 2.0 Origin - A-MEM: 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 2030. 6 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1GLM-5.3 Flash38.8#136
2Gemini 4 Argon38.8#14
3Qwen 3.8 27B32.1#219
4GPT-6 Luna29.5#105
5Granite 4.2 8B28.4#1561
6Qwen 3.5 9B20.5#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-spider-2-0-origin-a-mem · How It Works · Data refreshed daily, snapshot 2026-11-17.