Noometry

Model comparison

DeepSeek-V3.2-Exp vs Gemini 3 Deep Think

DeepSeek-V3.2-Exp has enough public results to be ranked (#78); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

DeepSeek-V3.2-Exp DeepSeek

44.3

Rank #78 Confirmed

Gemini 3 Deep Think Google

58.3

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 0 categories and Gemini 3 Deep Think in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 22.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 4% for DeepSeek-V3.2-Exp and 84.6% for Gemini 3 Deep Think.
  • DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.2-ExpGemini 3 Deep Think
ProviderDeepSeekGoogle
Noometry Index44.358.3
Released2025-09-292026-02-12
WeightsOpenProprietary
Context window164K—
Max output66K—
Input $ / M tokens$0.26—
Output $ / M tokens$0.38—
Results tracked493

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

DeepSeek-V3.2-Exp: 46.5 (#65), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
SWE-bench Verified (bash only)70%—
Aider Polyglot74.2%—
LMArena WebDev1362—
SWE-bench Multilingual59%—
SciCode38.9%—
WeirdML39.5%—
LMArena Coding1454—

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 32.7 (#59), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
Terminal-Bench39.6%—
APEX-Agents21.3%—
Berkeley Function Calling Leaderboard56.7%—
TheAgentCompany42.9%—
Vending-Bench 21,034—

Reasoning Gemini 3 Deep Think leads

DeepSeek-V3.2-Exp: 22.1 (#208), Gemini 3 Deep Think: 70.2 (#14)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
ARC-AGI-24%84.6%
ARC-AGI-157%96%
CritPt2.9%25.7%
Kagi LLM Benchmark52.2%—
NYT Connections (extended)36.7%—
Chess Puzzles14%—
Thematic Generalization65%—
LMArena Hard Prompts1434—
DTBench87.7%—
LMCA29.1%—
Epoch Capabilities Index146.27—

Math Not comparable

DeepSeek-V3.2-Exp: 41.7 (#87), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
MathArena Final-Answer Competitions57.7%—
OTIS Mock AIME 2024-202587.8%—
ProofBench8%—
LMArena Math1435—
FrontierMath (Feb 2025 set)22.1%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Not comparable

DeepSeek-V3.2-Exp: 51.7 (#66), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
GPQA Diamond83.4%—
Vectara Hallucination Rate5.3%—
LMArena Expert1436—

Multilingual Not comparable

DeepSeek-V3.2-Exp: 52.2 (#90), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
LMArena Non-English1409—
LMArena Chinese1461—
LMArena French1433—
LMArena German1440—
LMArena Japanese1374—
LMArena Korean1371—
LMArena Russian1424—
LMArena Spanish1440—

Instruction Following Not comparable

DeepSeek-V3.2-Exp: 74.5 (#93), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
LMArena Instruction Following1413—

Long Context Not comparable

DeepSeek-V3.2-Exp: 47.6 (#16), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
Fiction.LiveBench83.3%—
CL-bench13.2%—
CL-bench Life9.5%—
LMArena Longer Query1428—

Writing & Preference Not comparable

DeepSeek-V3.2-Exp: 62.4 (#77), Gemini 3 Deep Think: —

BenchmarkDeepSeek-V3.2-ExpGemini 3 Deep Think
LMArena Text1425—
LMArena Creative Writing1403—
EQ-Bench Creative Writing1515—
LMArena Multi-Turn1427—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Gemini 3 Deep Think?

DeepSeek-V3.2-Exp has enough public results to be ranked (#78); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

How many benchmarks do DeepSeek-V3.2-Exp and Gemini 3 Deep Think share?

3 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Gemini 3 Deep Think has 3.

Related comparisons

Go deeper