Verification Transport - AgentDojo - V-DELIBERATIVE - 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: Estimated already saturated. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemma 4 31B99.5#385
2Gemini 3.7 Flash99.2#38
3GPT-OSS-20B96#1163
4Gemma 4 26B A4B95.1#581
5Gemini 2.5 Flash93.5#467
6GPT-OSS-120B93.2#707
7Llama 4 Maverick76.5#1118

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-agentdojo-v-deliberative-macro-restoration-recovery · How It Works · Data refreshed daily, snapshot 2026-11-17.