New: Agent Index for knowledge work is live.Explore the index ↗
Compare models

Explore DeepSeek V3.2’s published benchmark results and provider offerings below. More comparable task results are needed to describe its strongest areas.

Updated: Data as of:
Compare this model

Strongest results

Strongest results for DeepSeek V3.2 in tracked evaluation cohorts
BenchmarkMeasuresScore
Humanity's Last Exam ↗Stable HLE — text-only subsetExpert reasoning24.6%#56 of 68

Model details

Open source / open weights2 benchmarks
Specifications for DeepSeek V3.2
ModelDeepSeek V3.2
Agent Index v1.2Insufficient coverage (0/7) · Preview
CreatorDeepSeek (opens in a new tab)
AvailabilityOpen source / open weights
Context sizeNot reported
Max outputNot reported
Knowledge cutoffNot reported
LicenseNot reported · Model weights ↗ (opens in a new tab)

Pricing and performance

Per provider and reported configuration. Prices are USD per 1M tokens.

No provider pricing or performance reports have been added for this model yet.

Reported benchmarks

All published results in our dataset, with versions, evaluation settings, and sources.

All published benchmark reports for DeepSeek V3.2
BenchmarkScoreEvaluation setupSource
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better40.8%Published comparison table; DeepSeek dagger denotes text-only. Other rows use full text and image set. · subset: text · Tools enabledMoonshot AI ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better25.1%Published comparison table; DeepSeek dagger denotes text-only. Other rows use full text and image set. · subset: text · No toolsMoonshot AI ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better24.6%question count: 2158 · reported precision decimals: 1 · DeepSeek V3.2; original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/deepseek-v3-2-reasoning · subset: text · No toolsArtificial Analysis (opens in a new tab)independent
π-BenchOverall · PROCProactivity (PROC) · Higher is better53.3%completeness score: 57.8 · completeness uncertainty: 3 · metric: Avg PROC · personas: 5 · proc uncertainty: 1.9 · selection: Overall rows; not per-persona averages. COMP is a separate metric and does not determine this ranking. · tasks: 100π-Bench research team ↗ (opens in a new tab)benchmark publisher