Verification Transport - AgentDojo - V-LLM - Compaction 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
1Gemini 3.7 Flash97.2#38
2Gemma 4 31B97.1#385
3GPT-OSS-20B97#1163
4Gemma 4 26B A4B96.9#581
5GPT-OSS-120B94.4#707
6Gemini 2.5 Flash88.1#467
7Llama 4 Maverick80.6#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-llm-compaction-restoration-recovery · How It Works · Data refreshed daily, snapshot 2026-11-17.