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

Top models

#ModelScoreOverall rank
1Gemma 4 31B2.8#385
2Gemini 3.7 Flash3.4#38
3Llama 4 Maverick21.1#1118
4GPT-OSS-20B22.3#1163
5Gemini 2.5 Flash31#467
6Gemma 4 26B A4B44#581
7GPT-OSS-120B55.7#707

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