Evolving Requirements - Evo+Comp FDAC-soft: leaderboard

61 frozen repository tasks, 207 requirement states. ClaudeCode2.1.74, 200ktoken context, high reasoning, provider-default sampling, network-disabled. Full one complete session; Evo one response/state; Evo+Comp initial plus<=2completion revisions/state; Hy4-Preview high feedbackgenerator20ktokens and<=2publicobservations/message. StrictPass allchecks; NodeCredit partialstate credit; FDAC feedback-discounted adaptivecorrectness. Pooled row withheld. Metric: Native score (%). Source: https://arxiv.org/html/2610.35488v1

Metric: Native score (%). Source: arxiv.org. Saturation forecast: Around 2029. 12 models tracked. Updated 17 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraHigh52.6#8
2GPT-5.6 SolHigh51.9#33
3Kimi K3High51.6#59
4DeepSeek V4.1 FlashHigh50.3#69
5Hy4 previewHigh49.6#75
6DeepSeek V4 FlashHigh49.3#265
7GLM-5.3High47.8#73
8DeepSeek V4 ProHigh44.8#198
9GLM-5.3 FlashHigh44.1#136
10Qwen 3.8 FlashHigh43.8#128
11Grok 4.6High41.8#47
12Hy3High27.9#211

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

Interactive version: theaggregate.ai/benchmark?slug=evolving-requirements-evo-pluscomp-fdac-soft · How It Works · Data refreshed daily, snapshot 2026-11-17.