Verification Transport - ATBench - V-LLM - Macro Restoration Recovery: leaderboard

Matched native/abstracted/restored executions; 7exactmodelbackbones; protocol andbenchmark split. OBA nativebalancedaccuracy; VTFR conditionedonnativecorrectjudgments; RRR conditionedontransportfailures; RDR restoreddegradation. Denominators differ andmustnotpool. Invalid/noverdict outcomes countedunderpaperoperationalfailurepolicy. Three abstractionboundaries independent. Full immutablepayload pins alldefinitions. Metric: Native rate (%). Source: https://arxiv.org/html/2611.18471v1

Metric: Native rate (%). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemma 4 31B89.2#385
2Gemini 2.5 Flash81.1#467
3Gemini 3.7 Flash79.5#38
4Llama 4 Maverick79.2#1118
5Gemma 4 26B A4B76.3#581
6GPT-OSS-120B67.6#707
7GPT-OSS-20B55.6#1163

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

Interactive version: theaggregate.ai/benchmark?slug=verification-transport-atbench-v-llm-macro-restoration-recovery · How It Works · Data refreshed daily, snapshot 2026-11-17.