DeepSeek V3.2 (High) — benchmark results
DeepSeek V3.2 evaluated at the high reasoning-effort setting. Provider: DeepSeek. Released 2025-12-01. Access: Open.
Unified ELO 1623 ± 91, rank #431 of 1776 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| NonoBench | 36.7 | Overall Accuracy (%) | 69.1 |
| EnterpriseOps-Gym | 23.8 | Task Success Rate (self-reported) | 47.6 |
| IOI | 10.67 | Score (self-reported) | 43.4 |
| Vals AI CaseLaw v2 | 55.41 | Accuracy (%) | 38.5 |
| FutureEval | 7.74 | Unified Forecasting Score | 37.8 |
| Vals AI ProofBench | 4 | Accuracy (%) | 8.4 |
| Finance Agent v1.1 | 2.35 | Score (self-reported) | 3.6 |
Interactive version: theaggregate.ai/model?slug=deepseek-v3-2-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.