HARE - Spider 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 September 2027. 6 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 78.3 | #14 |
| 2 | GPT-6 Luna | 77.4 | #105 |
| 3 | GLM-5.3 Flash | 76.9 | #136 |
| 4 | Qwen 3.8 27B | 75.9 | #219 |
| 5 | Qwen 3.5 9B | 73.1 | #822 |
| 6 | Granite 4.2 8B | 72.6 | #1561 |
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-origin-a-mem · How It Works · Data refreshed daily, snapshot 2026-11-17.