Verification Transport - AgentDojo - V-EVIDENCE - Native Operational Balanced Accuracy: 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 31B77.6#385
2Gemini 3.7 Flash76.5#38
3GPT-OSS-120B75.1#707
4GPT-OSS-20B73.5#1163
5Gemini 2.5 Flash72.7#467
6Gemma 4 26B A4B68.6#581
7Llama 4 Maverick61.5#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-evidence-native-operational-balanced-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-17.