Noometry

Model comparison

DeepSeek-V3.1 vs Gemini 3.7 Flash

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 42.2 on the Noometry Index. DeepSeek-V3.1 costs 3.5× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Gemini 3.7 Flash Google

59.8

Rank #11 Confirmed

Summary

  • They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 0 categories and Gemini 3.7 Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 27.3.
  • The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 50.4% for Gemini 3.7 Flash.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
  • Gemini 3.7 Flash accepts more context: 1.05M tokens versus 164K.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1Gemini 3.7 Flash
ProviderDeepSeekGoogle
Noometry Index42.259.8
Released2025-08-212026-08-13
WeightsOpenProprietary
Context window164K1.05M
Max output8K66K
Input $ / M tokens$0.25$0.75
Output $ / M tokens$0.95$3.75
Results tracked2744

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

Category by category

Coding Gemini 3.7 Flash leads

DeepSeek-V3.1: 39.8 (#140), Gemini 3.7 Flash: 55.7 (#19)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Coding14171499
DeepSWE—65.5%
FrontierCode—43.6%
LMArena WebDev—1593
FrontierSWE—20.3%
SciCode—59.8%
WeirdML38.4%—
ALE-Bench—904.3

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Gemini 3.7 Flash: 42.2 (#18)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
APEX-Agents—67.8%
Remote Labor Index—5%
GDP.pdf—23.8%

Reasoning Gemini 3.7 Flash leads

DeepSeek-V3.1: 27.3 (#109), Gemini 3.7 Flash: 70.1 (#12)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Hard Prompts14171497
DTBench82.7%96.8%
LMCA24.3%50.4%
Epoch Capabilities Index139.92157.72
ARC-AGI-2—84.6%
SimpleBench40%—
Kagi LLM Benchmark53.2%—
NYT Connections (extended)—94%
ARC-AGI-1—95.5%
CritPt—14.3%
Chess Puzzles—47%
Mystery Game Puzzles—37%
ForecastBench58—

Math Gemini 3.7 Flash leads

DeepSeek-V3.1: 36.1 (#125), Gemini 3.7 Flash: 69.5 (#18)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Math14201511
FrontierMath (Tiers 1-3)—71.6%
FrontierMath Tier 4—36.6%
OTIS Mock AIME 2024-2025—97.2%
ProofBench—58%

Knowledge Gemini 3.7 Flash leads

DeepSeek-V3.1: 43.0 (#86), Gemini 3.7 Flash: 69.8 (#4)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Expert14031508
GPQA Diamond—94.8%
SimpleQA Verified—69.2%
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

DeepSeek-V3.1: —, Gemini 3.7 Flash: 36.9 (#69)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Vision—1314
Furniture Assembly—26.7%

Multilingual Gemini 3.7 Flash leads

DeepSeek-V3.1: 51.8 (#100), Gemini 3.7 Flash: 57.8 (#7)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Non-English14001485
LMArena Chinese14701553
LMArena French14471512
LMArena German14121485
LMArena Japanese13741506
LMArena Korean13371486
LMArena Russian14051519
LMArena Spanish14291507

Instruction Following Gemini 3.7 Flash leads

DeepSeek-V3.1: 74.1 (#105), Gemini 3.7 Flash: 78.0 (#12)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Instruction Following14001486

Long Context Gemini 3.7 Flash leads

DeepSeek-V3.1: 36.3 (#227), Gemini 3.7 Flash: 45.8 (#28)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Longer Query14221493
Fiction.LiveBench52.8%—

Writing & Preference Gemini 3.7 Flash leads

DeepSeek-V3.1: 60.5 (#93), Gemini 3.7 Flash: 71.4 (#19)

BenchmarkDeepSeek-V3.1Gemini 3.7 Flash
LMArena Text14201487
LMArena Creative Writing14011490
EQ-Bench Creative Writing14361723
LMArena Multi-Turn14081495

Frequently asked questions

Is DeepSeek-V3.1 better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 42.2 on the Noometry Index. DeepSeek-V3.1 costs 3.5× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

Which is cheaper, DeepSeek-V3.1 or Gemini 3.7 Flash?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

Is DeepSeek-V3.1 or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 39.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and Gemini 3.7 Flash share?

21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 3.7 Flash has 44.

Related comparisons

Go deeper