Noometry

Model comparison

DeepSeek-V3.2-Exp vs Gemini 3 Flash Preview

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.3 on the Noometry Index. DeepSeek-V3.2-Exp costs 3.9× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

DeepSeek-V3.2-Exp DeepSeek

44.3

Rank #78 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 37 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 1 category and Gemini 3 Flash Preview in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 22.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 36.7% for DeepSeek-V3.2-Exp and 83.1% for Gemini 3 Flash Preview.
  • DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 164K.
  • DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.2-ExpGemini 3 Flash Preview
ProviderDeepSeekGoogle
Noometry Index44.352.3
Released2025-09-292025-12-17
WeightsOpenProprietary
Context window164K1.05M
Max output66K66K
Input $ / M tokens$0.26$0.50
Output $ / M tokens$0.38$3
Results tracked4959

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

Category by category

Coding Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 46.5 (#65), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
SWE-bench Verified (bash only)70%75.8%
LMArena WebDev13621439
SWE-bench Multilingual59%72.7%
WeirdML39.5%61.6%
LMArena Coding14541460
SWE-bench Verified—75.4%
Aider Polyglot74.2%—
SciCode38.9%—
GSO—9.8%
ALE-Bench—1,367

Agentic & Tool Use Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 32.7 (#59), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
Terminal-Bench39.6%64.3%
Vending-Bench 21,0343,635
APEX-Agents21.3%—
Berkeley Function Calling Leaderboard56.7%—
TheAgentCompany42.9%—
τ²-bench Airline—82.5%
τ²-bench Banking—27.3%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
DeepResearch Bench—49.8%
BALROG—48.1%
GDP.pdf—10%
LMArena Search—1198

Reasoning Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 22.1 (#208), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
ARC-AGI-24%33.6%
NYT Connections (extended)36.7%83.1%
ARC-AGI-157%84.7%
Chess Puzzles14%40%
LMArena Hard Prompts14341465
DTBench87.7%89.1%
LMCA29.1%43.1%
Epoch Capabilities Index146.27151.8
SimpleBench—61.1%
Kagi LLM Benchmark52.2%—
CritPt2.9%—
Thematic Generalization65%—
Mystery Game Puzzles—26%
ForecastBench—58.5

Math Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 41.7 (#87), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
MathArena Final-Answer Competitions57.7%67.6%
OTIS Mock AIME 2024-202587.8%95.6%
ProofBench8%15%
LMArena Math14351473
FrontierMath (Feb 2025 set)22.1%35.6%
FrontierMath Tier 4 (v1)2.1%4.2%
FrontierMath (Tiers 1-3)—51.2%
FrontierMath Tier 4—17.1%

Knowledge Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 51.7 (#66), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
GPQA Diamond83.4%89.4%
Vectara Hallucination Rate5.3%13.5%
LMArena Expert14361462
SimpleQA Verified—66.8%

Multimodal Not comparable

DeepSeek-V3.2-Exp: —, Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
LMArena Vision—1285
GeoBench—88%
VPCT—72.6%
Blueprint-Bench 2—0%
LMArena Document—1413

Multilingual Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 52.2 (#90), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
LMArena Non-English14091458
LMArena Chinese14611511
LMArena French14331477
LMArena German14401497
LMArena Japanese13741489
LMArena Korean13711443
LMArena Russian14241480
LMArena Spanish14401469

Instruction Following Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 74.5 (#93), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
LMArena Instruction Following14131437

Long Context DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 47.6 (#16), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
LMArena Longer Query14281452
Fiction.LiveBench83.3%—
CL-bench13.2%—
CL-bench Life9.5%—

Writing & Preference Gemini 3 Flash Preview leads

DeepSeek-V3.2-Exp: 62.4 (#77), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkDeepSeek-V3.2-ExpGemini 3 Flash Preview
LMArena Text14251466
LMArena Creative Writing14031457
LMArena Multi-Turn14271471
EQ-Bench Creative Writing1515—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.3 on the Noometry Index. DeepSeek-V3.2-Exp costs 3.9× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Which is cheaper, DeepSeek-V3.2-Exp or Gemini 3 Flash Preview?

DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

Is DeepSeek-V3.2-Exp or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 46.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.2-Exp and Gemini 3 Flash Preview share?

37 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper