Noometry

Model comparison

DeepSeek LLM 67B vs Gemma 4 31B IT

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 8.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 73.3% for Gemma 4 31B IT.

Side by side

DeepSeek LLM 67BGemma 4 31B IT
ProviderDeepSeekGoogle
Noometry Index24.943.5
Released2023-11-292026-04-02
WeightsOpenOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.09
Output $ / M tokens—$0.34
Results tracked1535

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

Category by category

Coding Gemma 4 31B IT leads

DeepSeek LLM 67B: 31.9 (#278), Gemma 4 31B IT: 42.3 (#108)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
LMArena Coding10961459
LMArena WebDev—1366
SciCode—43.4%
WeirdML—52.3%
ALE-Bench—925.5

Reasoning Gemma 4 31B IT leads

DeepSeek LLM 67B: 16.5 (#304), Gemma 4 31B IT: 27.2 (#122)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
Chess Puzzles0%5%
LMArena Hard Prompts10701448
Epoch Capabilities Index110.5142.74
Kagi LLM Benchmark—63.5%
NYT Connections (extended)—70.6%
CritPt—1.4%
Thematic Generalization—53%
DTBench—82.7%
LMCA—39.3%
Surface Evolver Bench—30.6%

Math Gemma 4 31B IT leads

DeepSeek LLM 67B: 8.7 (#324), Gemma 4 31B IT: 43.2 (#81)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
OTIS Mock AIME 2024-20250.8%73.3%
LMArena Math11081465
MATH Level 56.4%—

Knowledge Gemma 4 31B IT leads

DeepSeek LLM 67B: 7.0 (#313), Gemma 4 31B IT: 37.9 (#151)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
GPQA Diamond24.6%75.8%
SimpleQA Verified—10.4%
Vectara Hallucination Rate—7.4%
LMArena Expert—1465

Multimodal Not comparable

DeepSeek LLM 67B: —, Gemma 4 31B IT: 41.6 (#34)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
LMArena Vision—1277
LMArena Document—1425

Multilingual Gemma 4 31B IT leads

DeepSeek LLM 67B: 29.4 (#267), Gemma 4 31B IT: 53.8 (#57)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
LMArena Non-English10731431
LMArena Chinese11321476
LMArena French—1435
LMArena Russian—1460
LMArena Spanish—1444

Instruction Following Gemma 4 31B IT leads

DeepSeek LLM 67B: 55.4 (#277), Gemma 4 31B IT: 75.5 (#61)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
LMArena Instruction Following10791433

Long Context Gemma 4 31B IT leads

DeepSeek LLM 67B: 33.1 (#265), Gemma 4 31B IT: 44.2 (#71)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
LMArena Longer Query10921446

Writing & Preference Gemma 4 31B IT leads

DeepSeek LLM 67B: 31.6 (#282), Gemma 4 31B IT: 60.5 (#96)

BenchmarkDeepSeek LLM 67BGemma 4 31B IT
LMArena Text11051443
LMArena Creative Writing10671415
LMArena Multi-Turn10821452
EQ-Bench Creative Writing—1368
EQ-Bench 4—1120

Frequently asked questions

Is DeepSeek LLM 67B better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Gemma 4 31B IT share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 4 31B IT has 35.

Related comparisons

Go deeper