ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek V3.2vsDeepSeek V4 Pro

DeepSeek V4 Pro leads 3 of 3 shared benchmarks. DeepSeek V4 Pro has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 3
DeepSeek V4 Pro leads
Cheaper per token
list price, input + output
Larger context
DeepSeek V4 Pro
1M tokens
Provider uptime (30d)
100%
DeepSeek
DeepSeek V3.2
DeepSeek · released 2025-12-01
text
Context
131K
Max out
66K
Input /1M
Output /1M
Cached /1M
Scores
8 · 7 core
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
Context
1M
Max out
384K
Input /1M
$0.435
Output /1M
$0.87
Cached /1M
$0.004
Scores
11 · 9 core
Quality

Benchmark matrix

BenchmarkDeepSeek V3.2DeepSeek V4 ProΔEdge
Reported by both · 3
GPQA Diamond82.4% 90.9% epoch-8.5 ptDeepSeek V4 Pro
AIME 202694.2% matharena96.7% matharena-2.5 ptDeepSeek V4 Pro
LMArena Elo1424.8 1450.6 -25.8DeepSeek V4 Pro
Only DeepSeek V3.2 reports · 4
SWE-bench Verified73.1% not reported
MMLU-Pro85% not reported
AIME 202593.1% not reported
Humanity's Last Exam (no tools)25.1% not reported
Only DeepSeek V4 Pro reports · 8
DeepSWE v1.1not reported62.7%
FrontierMath Tier 4 v2 (Epoch AI run)not reported2.4% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported45.3% epoch
Humanity's Last Exam (with tools)not reported60%
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported96.7% epoch
SimpleQA Verifiednot reported47% epoch
SWE-bench Verified (Epoch AI run)not reported77.6% epoch
Terminal-Bench 2.1not reported87.9%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek V3.2 minus DeepSeek V4 Pro in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecDeepSeek V3.2DeepSeek V4 ProEdge
Context window131K tokens1M tokensDeepSeek V4 Pro
Max output66K tokens384K tokensDeepSeek V4 Pro
Input price / 1M$0.435
Output price / 1M$0.87
Cached input / 1M$0.004
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.31
ModalitiestexttextTie
Released2025-12-012026-08-13
Cited benchmark scores811
Reliability

DeepSeek status

All providers
More matchups

DeepSeek V4 Pro vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek V3.2 and DeepSeek V4 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.