Verification Transport - AgentDojo - V-DELIBERATIVE - Macro VTFR: 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: Not forecast. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemma 4 26B A4B9.5#581
2Llama 4 Maverick31.2#1118
3Gemini 2.5 Flash41.4#467
4GPT-OSS-20B41.5#1163
5GPT-OSS-120B86.9#707
6Gemma 4 31B93.1#385
7Gemini 3.7 Flash95.1#38

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-vtfr · How It Works · Data refreshed daily, snapshot 2026-11-17.