Verification Transport - PlanRewardBench (PRB) - V-EVIDENCE - 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: Around December 2027. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemma 4 31B15.4#385
2Gemma 4 26B A4B26.7#581
3GPT-OSS-20B40.7#1163
4Gemini 2.5 Flash45.5#467
5Gemini 3.7 Flash46.7#38
6GPT-OSS-120B51.2#707
7Llama 4 Maverick59.2#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-planrewardbench-prb-v-evidence-macro-vtfr · How It Works · Data refreshed daily, snapshot 2026-11-17.