Model comparison

Gemma 4 31B IT vs Llama2 70b Steerlm Chat

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 31.8 on the Noometry Index.

Last verified . 9 shared benchmarks.

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

Llama2 70b Steerlm Chat NVIDIA

31.8

Rank #268 Confirmed

Summary

  • They share 9 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 31.6.

Side by side

Gemma 4 31B IT and Llama2 70b Steerlm Chat specifications
Gemma 4 31B ITLlama2 70b Steerlm Chat
ProviderGoogleNVIDIA
Noometry Index43.531.8
Released2026-04-02—
WeightsOpenOpen
Context window262K—
Max output33K—
Input $ / M tokens$0.09—
Output $ / M tokens$0.34—
Results tracked359

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

Category by category

Coding Gemma 4 31B IT leads

Gemma 4 31B IT: 42.3 (#108), Llama2 70b Steerlm Chat: 29.9 (#300)

Coding benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Coding14591025
LMArena WebDev1366—
SciCode43.4%—
WeirdML52.3%—
ALE-Bench925.5—

Reasoning Gemma 4 31B IT leads

Gemma 4 31B IT: 27.2 (#122), Llama2 70b Steerlm Chat: 20.0 (#246)

Reasoning benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Hard Prompts14481047
Kagi LLM Benchmark63.5%—
NYT Connections (extended)70.6%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Gemma 4 31B IT leads

Gemma 4 31B IT: 43.2 (#81), Llama2 70b Steerlm Chat: 31.3 (#226)

Math benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Math14651072
OTIS Mock AIME 2024-202573.3%—

Knowledge Not comparable

Gemma 4 31B IT: 37.9 (#151), Llama2 70b Steerlm Chat: —

Knowledge benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—
LMArena Expert1465—

Multimodal Not comparable

Gemma 4 31B IT: 41.6 (#34), Llama2 70b Steerlm Chat: —

Multimodal benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Vision1277—
LMArena Document1425—

Multilingual Gemma 4 31B IT leads

Gemma 4 31B IT: 53.8 (#57), Llama2 70b Steerlm Chat: 28.8 (#270)

Multilingual benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Non-English14311063
LMArena Chinese1476—
LMArena French1435—
LMArena Russian1460—
LMArena Spanish1444—

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.5 (#61), Llama2 70b Steerlm Chat: 54.2 (#279)

Instruction Following benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Instruction Following14331060

Long Context Gemma 4 31B IT leads

Gemma 4 31B IT: 44.2 (#71), Llama2 70b Steerlm Chat: 30.4 (#288)

Long Context benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Longer Query1446998

Writing & Preference Gemma 4 31B IT leads

Gemma 4 31B IT: 60.5 (#96), Llama2 70b Steerlm Chat: 31.6 (#283)

Writing & Preference benchmarks
BenchmarkGemma 4 31B ITLlama2 70b Steerlm Chat
LMArena Text14431098
LMArena Creative Writing14151091
LMArena Multi-Turn14521058
EQ-Bench Creative Writing1368—
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than Llama2 70b Steerlm Chat?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 31.8 on the Noometry Index.

Is Gemma 4 31B IT or Llama2 70b Steerlm Chat better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 29.9 in the Noometry coding category.

How many benchmarks do Gemma 4 31B IT and Llama2 70b Steerlm Chat share?

9 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Llama2 70b Steerlm Chat has 9.

Related comparisons

Go deeper