DeepSeek V3P2: benchmark results
Provider: DeepSeek. Released 2025-12-01. Access: Open.
Unified ELO 1800 ± 28, rank #155 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI MGSM | 90.87 | Accuracy (%) | 56.9 |
| IOI | 14.42 | Score (self-reported) | 51.7 |
| MMLU Pro | 83.06 | Score (%) | 49.2 |
| GPQA Diamond | 76.26 | Score (%) | 46 |
| MedQA | 89.45 | Score (%) | 45.7 |
| AIME | 64.79 | Score (%) | 43.2 |
| ProofBench | 8 | Score (self-reported) | 19.3 |
| CorpFin v2 | 47.94 | Score (%) | 17.6 |
| LegalBench | 65.96 | Score (%) | 10.2 |
| Vals AI Finance Agent | 0 | Accuracy (%) | 0.8 |
Interactive version: theaggregate.ai/model?slug=deepseek-v3p2 · How It Works · Data refreshed daily, snapshot 2026-09-19.