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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash | 3.1 | #38 |
| 2 | Gemma 4 26B A4B | 3.6 | #581 |
| 3 | Gemma 4 31B | 3.7 | #385 |
| 4 | GPT-OSS-120B | 5.7 | #707 |
| 5 | Llama 4 Maverick | 8.4 | #1118 |
| 6 | GPT-OSS-20B | 10.5 | #1163 |
| 7 | Gemini 2.5 Flash | 28.3 | #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.