Evolving Requirements - Evo+Comp FDAC: 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 AstraHigh46.5#8
2GPT-5.6 SolHigh45.4#33
3Kimi K3High44.2#59
4Hy4 previewHigh42.7#75
5DeepSeek V4 FlashHigh41.2#265
6DeepSeek V4.1 FlashHigh40.8#69
7GLM-5.3High40.5#73
8Qwen 3.8 FlashHigh37.3#128
9GLM-5.3 FlashHigh37.2#136
10Grok 4.6High37.1#47
11DeepSeek V4 ProHigh36.7#198
12Hy3High21.2#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 · How It Works · Data refreshed daily, snapshot 2026-11-17.