Noometry

Model comparison

Gemma 4 31B IT vs Qwen1.5-72B

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 30.3 on the Noometry Index.

Last verified . 15 shared benchmarks.

Gemma 4 31B IT Google

43.2

Rank #85 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemma 4 31B IT leads 37.9 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 75.8% for Gemma 4 31B IT and 28.8% for Qwen1.5-72B.

Side by side

Gemma 4 31B ITQwen1.5-72B
ProviderGoogleAlibaba (Qwen)
Noometry Index43.230.3
Released2026-04-022024-02-04
WeightsOpenOpen
Context window262K—
Max output33K—
Input $ / M tokens$0.09—
Output $ / M tokens$0.34—
Results tracked3522

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: 41.9 (#98), Qwen1.5-72B: 31.4 (#272)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Coding14591166
LMArena WebDev1364—
SciCode43.4%—
WeirdML52.3%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench925.5—
HumanEval+—59.1%
MBPP+—61.6%

Reasoning Gemma 4 31B IT leads

Gemma 4 31B IT: 26.4 (#119), Qwen1.5-72B: 21.2 (#201)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Hard Prompts14481148
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: 41.3 (#72), Qwen1.5-72B: 30.7 (#205)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Math14641164
OTIS Mock AIME 2024-202573.3%—

Knowledge Gemma 4 31B IT leads

Gemma 4 31B IT: 37.9 (#141), Qwen1.5-72B: 11.5 (#295)

BenchmarkGemma 4 31B ITQwen1.5-72B
GPQA Diamond75.8%28.8%
LMArena Expert14651136
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 4 31B IT: 41.0 (#32), Qwen1.5-72B: —

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Vision1278—
LMArena Document1425—

Multilingual Gemma 4 31B IT leads

Gemma 4 31B IT: 54.0 (#52), Qwen1.5-72B: 33.4 (#248)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Non-English14311135
LMArena Chinese14781186
LMArena French14361158
LMArena Russian14621104
LMArena Spanish14431110
LMArena German—1084
LMArena Japanese—1061
LMArena Korean—1049

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.6 (#58), Qwen1.5-72B: 59.6 (#251)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Instruction Following14331142

Long Context Gemma 4 31B IT leads

Gemma 4 31B IT: 44.2 (#67), Qwen1.5-72B: 35.0 (#238)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Longer Query14461157

Writing & Preference Gemma 4 31B IT leads

Gemma 4 31B IT: 60.7 (#92), Qwen1.5-72B: 37.4 (#253)

BenchmarkGemma 4 31B ITQwen1.5-72B
LMArena Text14431166
LMArena Creative Writing14161137
LMArena Multi-Turn14521160
EQ-Bench Creative Writing1368—
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than Qwen1.5-72B?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 30.3 on the Noometry Index.

Is Gemma 4 31B IT or Qwen1.5-72B better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 31.4 in the Noometry coding category.

How many benchmarks do Gemma 4 31B IT and Qwen1.5-72B share?

15 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper