Verification Transport - PlanRewardBench (PRB) - V-EVIDENCE - Macro Restoration Degradation: 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 Flash3.1#38
2Gemma 4 26B A4B3.6#581
3Gemma 4 31B3.7#385
4GPT-OSS-120B5.7#707
5Llama 4 Maverick8.4#1118
6GPT-OSS-20B10.5#1163
7Gemini 2.5 Flash28.3#467

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-planrewardbench-prb-v-evidence-macro-restoration-degradation · How It Works · Data refreshed daily, snapshot 2026-11-17.