Noometry

Model comparison

Gemma 3 4B vs Qwen2.5-VL 72B Instruct

Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index. Gemma 3 4B costs 84× less per token, which makes it the better buy when Qwen2.5-VL 72B Instruct's lead doesn't matter for your workload.

Last verified . 1 shared benchmarks.

Gemma 3 4B Google

27.9

Rank #320 Confirmed

Qwen2.5-VL 72B Instruct Alibaba (Qwen)

29.4

Rank #298 Confirmed

Summary

  • They share 1 benchmark with published results for both. Gemma 3 4B scores higher in 1 category and Qwen2.5-VL 72B Instruct in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen2.5-VL 72B Instruct leads 20.0 to 12.7.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 36% for Qwen2.5-VL 72B Instruct.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.

Side by side

Gemma 3 4BQwen2.5-VL 72B Instruct
ProviderGoogleAlibaba (Qwen)
Noometry Index27.929.4
Released2025-03-122024-09
WeightsOpenOpen
Context window131K131K
Max output4K8K
Input $ / M tokens$0.04$2.80
Output $ / M tokens$0.08$8.40
Results tracked226

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

Category by category

Coding Not comparable

Gemma 3 4B: 35.3 (#214), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
LMArena Coding1230—

Agentic & Tool Use Gemma 3 4B leads

Gemma 3 4B: 20.7 (#134), Qwen2.5-VL 72B Instruct: 18.4 (#136)

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
Berkeley Function Calling Leaderboard19.6%—
OSWorld—5%

Reasoning Qwen2.5-VL 72B Instruct leads

Gemma 3 4B: 12.7 (#330), Qwen2.5-VL 72B Instruct: 20.0 (#228)

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
Kagi LLM Benchmark25.2%36%
Chess Puzzles0%—
LMArena Hard Prompts1253—
DTBench50.9%—
LMCA2.8%—
Epoch Capabilities Index116.02—

Math Not comparable

Gemma 3 4B: 15.8 (#286), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
OTIS Mock AIME 2024-20257.5%—
LMArena Math1239—

Knowledge Not comparable

Gemma 3 4B: 11.8 (#294), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
GPQA Diamond23.2%—
Vectara Hallucination Rate6.4%—
LMArena Expert1223—

Multimodal Not comparable

Gemma 3 4B: —, Qwen2.5-VL 72B Instruct: 32.9 (#92)

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
LMArena Vision—1107
Video-MME—73.5%
GeoBench—62%
SpatialViz-Bench—33.3%

Multilingual Not comparable

Gemma 3 4B: 42.7 (#189), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
LMArena Non-English1273—
LMArena German1281—
LMArena Russian1294—

Instruction Following Not comparable

Gemma 3 4B: 65.4 (#219), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
LMArena Instruction Following1239—

Long Context Not comparable

Gemma 3 4B: 38.6 (#189), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
LMArena Longer Query1274—

Writing & Preference Not comparable

Gemma 3 4B: 42.2 (#234), Qwen2.5-VL 72B Instruct: —

BenchmarkGemma 3 4BQwen2.5-VL 72B Instruct
LMArena Text1291—
LMArena Creative Writing1270—
EQ-Bench Creative Writing1068—
LMArena Multi-Turn1255—

Frequently asked questions

Is Gemma 3 4B better than Qwen2.5-VL 72B Instruct?

Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index. Gemma 3 4B costs 84× less per token, which makes it the better buy when Qwen2.5-VL 72B Instruct's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 4B or Qwen2.5-VL 72B Instruct?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 4B and Qwen2.5-VL 72B Instruct share?

1 benchmark has published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.

Related comparisons

Go deeper