ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek V3.2vsGemini 2.5 Pro

DeepSeek V3.2 leads 3 of 5 shared benchmarks. Gemini 2.5 Pro has the larger context window (1.0M tokens).

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

Shared benchmarks
3 – 2
DeepSeek V3.2 leads
Cheaper per token
list price, input + output
Larger context
Gemini 2.5 Pro
1.0M tokens
Provider uptime (30d)
100% · 100%
DeepSeek · Google
DeepSeek V3.2
DeepSeek · released 2025-12-01
text
Context
131K
Max out
66K
Input /1M
Output /1M
Cached /1M
Scores
8 · 7 core
Gemini 2.5 Pro
Google · released 2025-06-17
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$1.25
Output /1M
$10
Cached /1M
$0.125
Scores
14 · 9 core
Quality

Benchmark matrix

BenchmarkDeepSeek V3.2Gemini 2.5 ProΔEdge
Reported by both · 5
SWE-bench Verified73.1% 59.6% +13.5 ptDeepSeek V3.2
GPQA Diamond82.4% 86.4% -4 ptGemini 2.5 Pro
AIME 202593.1% 88% +5.1 ptDeepSeek V3.2
Humanity's Last Exam (no tools)25.1% 21.6% +3.5 ptDeepSeek V3.2
LMArena Elo1424.8 1457.8 -33Gemini 2.5 Pro
Only DeepSeek V3.2 reports · 2
MMLU-Pro85% not reported
AIME 202694.2% matharenanot reported
Only Gemini 2.5 Pro reports · 7
Aider Polyglotnot reported82.2%
FrontierMath Tier 4 v2 (Epoch AI run)not reported0% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported24.6% epoch
LiveCodeBenchnot reported74.2%
MMMUnot reported82%
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported84.7% epoch
SWE-bench Verified (Epoch AI run)not reported57.6% epoch
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 Gemini 2.5 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 V3.2Gemini 2.5 ProEdge
Context window131K tokens1.0M tokensGemini 2.5 Pro
Max output66K tokens66K tokensTie
Input price / 1M$1.25
Output price / 1M$10
Cached input / 1M$0.125
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$11.25
Modalitiestexttext · vision · audioGemini 2.5 Pro
Released2025-12-012025-06-17
Cited benchmark scores814
Reliability

Provider status

All providers
More matchups

Gemini 2.5 Pro vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek V3.2 and Gemini 2.5 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.