Noometry

Model comparison

DeepSeek V4 Pro vs Gemini 3.1 Flash Lite

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 40.4 on the Noometry Index.

Last verified . 33 shared benchmarks.

DeepSeek V4 Pro DeepSeek

54.2

Rank #28 Confirmed

Gemini 3.1 Flash Lite Google

40.4

Rank #141 Confirmed

Summary

  • They share 33 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 9 categories and Gemini 3.1 Flash Lite in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.4 to 22.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 91.3% for DeepSeek V4 Pro and 8.2% for Gemini 3.1 Flash Lite.
  • Both cost about the same: $0.43 input and $0.87 output per million tokens.
  • Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 1M.
  • DeepSeek V4 Pro has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 ProGemini 3.1 Flash Lite
ProviderDeepSeekGoogle
Noometry Index54.240.4
Released2026-04-242026-03-03
WeightsOpenProprietary
Context window1M1.05M
Max output393K66K
Input $ / M tokens$0.43$0.25
Output $ / M tokens$0.87$1.50
Results tracked4838

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

Category by category

Coding DeepSeek V4 Pro leads

DeepSeek V4 Pro: 52.2 (#31), Gemini 3.1 Flash Lite: 37.5 (#179)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
LMArena WebDev15821256
SciCode51%41.9%
WeirdML66.2%52.2%
LMArena Coding14701400
ALE-Bench1,403797.73
SWE-bench Verified77.6%—
FrontierCode28.6%—

Agentic & Tool Use DeepSeek V4 Pro leads

DeepSeek V4 Pro: 32.7 (#54), Gemini 3.1 Flash Lite: 29.9 (#72)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
APEX-Agents47.3%—
DeepResearch Bench—37.3%
Vending-Bench 23,285—

Reasoning DeepSeek V4 Pro leads

DeepSeek V4 Pro: 56.4 (#22), Gemini 3.1 Flash Lite: 22.3 (#181)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
Kagi LLM Benchmark53.5%67.2%
NYT Connections (extended)91.3%8.2%
CritPt18%1.1%
Chess Puzzles47%25%
LMArena Hard Prompts14611407
DTBench93.9%76.8%
LMCA45.5%35%
Epoch Capabilities Index155.39144.45
ForecastBench56.154.4
ARC-AGI-261.3%—
ARC-AGI-190.5%—
EnigmaEval—3%
Thematic Generalization—63.3%
Mystery Game Puzzles43%—
Surface Evolver Bench40%—

Math DeepSeek V4 Pro leads

DeepSeek V4 Pro: 64.6 (#24), Gemini 3.1 Flash Lite: 39.5 (#82)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
FrontierMath (Tiers 1-3)64.6%27.7%
OTIS Mock AIME 2024-202598.6%80%
LMArena Math14551427
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.6%—
ProofBench50%—

Knowledge DeepSeek V4 Pro leads

DeepSeek V4 Pro: 59.5 (#28), Gemini 3.1 Flash Lite: 41.7 (#95)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
GPQA Diamond91.7%81.8%
Vectara Hallucination Rate8.6%8.2%
LMArena Expert14631397
Humanity's Last Exam—8.6%
SimpleQA Verified52.9%—

Multimodal Not comparable

DeepSeek V4 Pro: —, Gemini 3.1 Flash Lite: 38.7 (#57)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
LMArena Vision—1240

Multilingual DeepSeek V4 Pro leads

DeepSeek V4 Pro: 54.5 (#44), Gemini 3.1 Flash Lite: 52.5 (#82)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
LMArena Non-English14381410
LMArena Chinese14861461
LMArena French14731423
LMArena German14581429
LMArena Japanese14481411
LMArena Korean14521393
LMArena Russian14521420
LMArena Spanish14571420

Instruction Following DeepSeek V4 Pro leads

DeepSeek V4 Pro: 76.3 (#44), Gemini 3.1 Flash Lite: 72.9 (#126)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
LMArena Instruction Following14481376

Long Context DeepSeek V4 Pro leads

DeepSeek V4 Pro: 45.0 (#49), Gemini 3.1 Flash Lite: 42.5 (#117)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
LMArena Longer Query14591394
CL-bench Life13.5%—

Writing & Preference DeepSeek V4 Pro leads

DeepSeek V4 Pro: 65.6 (#45), Gemini 3.1 Flash Lite: 61.0 (#90)

BenchmarkDeepSeek V4 ProGemini 3.1 Flash Lite
LMArena Text14511416
LMArena Creative Writing14461401
LMArena Multi-Turn14671417
EQ-Bench Creative Writing1553—
EQ-Bench 41166—

Frequently asked questions

Is DeepSeek V4 Pro better than Gemini 3.1 Flash Lite?

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 40.4 on the Noometry Index.

Which is cheaper, DeepSeek V4 Pro or Gemini 3.1 Flash Lite?

DeepSeek V4 Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Gemini 3.1 Flash Lite lists at $0.25 and $1.50.

Is DeepSeek V4 Pro or Gemini 3.1 Flash Lite better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 1M.

How many benchmarks do DeepSeek V4 Pro and Gemini 3.1 Flash Lite share?

33 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Gemini 3.1 Flash Lite has 38.

Related comparisons

Go deeper