Verification Transport - AgentDojo - V-EVIDENCE - Delegation 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: Around February 2027. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemma 4 26B A4B9.2#581
2Gemma 4 31B12.1#385
3Gemini 2.5 Flash13.9#467
4GPT-OSS-20B16#1163
5Llama 4 Maverick25.5#1118
6GPT-OSS-120B34#707
7Gemini 3.7 Flash96.4#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-evidence-delegation-vtfr · How It Works · Data refreshed daily, snapshot 2026-11-17.