Noometry

Model comparison

DeepSeek-V3.1-Terminus vs Gemini 4 Argon

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 43.1 on the Noometry Index.

Last verified . 12 shared benchmarks.

DeepSeek-V3.1-Terminus DeepSeek

43.1

Rank #97 Confirmed

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Summary

  • They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Gemini 4 Argon in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 4 Argon leads 73.9 to 38.5.
  • The biggest single-benchmark swing is CritPt: 1.7% for DeepSeek-V3.1-Terminus and 27.1% for Gemini 4 Argon.
  • DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1-TerminusGemini 4 Argon
ProviderDeepSeekGoogle
Noometry Index43.156.5
Released2025-09-222026-09-30
WeightsOpenProprietary
Context window164K—
Max output147K—
Input $ / M tokens$0.27—
Output $ / M tokens$1—
Results tracked1621

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

Category by category

Coding Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 42.0 (#113), Gemini 4 Argon: 62.0 (#9)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
SciCode40.6%61.8%
LMArena Coding14261550
LMArena WebDev—1678
FrontierSWE—55%
ALE-Bench745.17—

Agentic & Tool Use Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 4 Argon: 49.2 (#8)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
APEX-Agents—82.2%
Vending-Bench 2—13,718

Reasoning Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 26.4 (#133), Gemini 4 Argon: 44.2 (#47)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
CritPt1.7%27.1%
LMArena Hard Prompts14261548
Kagi LLM Benchmark57.4%—
DTBench81.3%—
LMCA28.6%—

Math Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 38.5 (#137), Gemini 4 Argon: 73.9 (#17)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
LMArena Math14021536
ProofBench—99%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 4 Argon: 43.9 (#89)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
LMArena Expert—1553

Multimodal Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 4 Argon: 46.5 (#14)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
Blueprint-Bench 2—54.4%

Multilingual Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 52.1 (#92), Gemini 4 Argon: 60.3 (#1)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
LMArena Non-English14071523
LMArena Russian14361537
LMArena Chinese—1610
LMArena Spanish—1497

Instruction Following Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 74.0 (#106), Gemini 4 Argon: 80.1 (#2)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
LMArena Instruction Following14041538

Long Context Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 43.4 (#97), Gemini 4 Argon: 47.6 (#15)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
LMArena Longer Query14211549

Writing & Preference Gemini 4 Argon leads

DeepSeek-V3.1-Terminus: 61.0 (#92), Gemini 4 Argon: 71.4 (#19)

BenchmarkDeepSeek-V3.1-TerminusGemini 4 Argon
LMArena Text14191534
LMArena Creative Writing14031531
LMArena Multi-Turn14111557

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Gemini 4 Argon?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 43.1 on the Noometry Index.

Is DeepSeek-V3.1-Terminus or Gemini 4 Argon better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 42.0 in the Noometry coding category.

How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 4 Argon share?

12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 4 Argon has 21.

Related comparisons

Go deeper