Verification Transport - ATBench - V-DELIBERATIVE - Macro 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash | 95.5 | #38 |
| 2 | Gemma 4 31B | 85.8 | #385 |
| 3 | Llama 4 Maverick | 83.4 | #1118 |
| 4 | Gemma 4 26B A4B | 82.9 | #581 |
| 5 | Gemini 2.5 Flash | 81.8 | #467 |
| 6 | GPT-OSS-20B | 74.2 | #1163 |
| 7 | GPT-OSS-120B | 71.4 | #707 |
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-atbench-v-deliberative-macro-restoration-recovery · How It Works · Data refreshed daily, snapshot 2026-11-17.