Noometry

Model comparison

Gemma 3 12B vs Qwen2.5 7B Instruct

Gemma 3 12B is the stronger model overall, scoring 31.8 to 28.6 on the Noometry Index.

Last verified . 6 shared benchmarks.

Gemma 3 12B Google

31.8

Rank #255 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

28.6

Rank #314 Confirmed

Summary

  • They share 6 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Qwen2.5 7B Instruct in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 17.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 2.5% for Qwen2.5 7B Instruct.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.

Side by side

Gemma 3 12BQwen2.5 7B Instruct
ProviderGoogleAlibaba (Qwen)
Noometry Index31.828.6
Released2025-03-122024-09
WeightsOpenOpen
Context window131K131K
Max output8K8K
Input $ / M tokens$0.05$0.17
Output $ / M tokens$0.15$0.70
Results tracked2415

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

Category by category

Coding Qwen2.5 7B Instruct leads

Gemma 3 12B: 31.2 (#276), Qwen2.5 7B Instruct: 35.9 (#204)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
SciCode17.4%—
BigCodeBench Instruct—37.6%
LMArena Coding1281—
BigCodeBench Complete—46.1%

Agentic & Tool Use Gemma 3 12B leads

Gemma 3 12B: 25.3 (#101), Qwen2.5 7B Instruct: 23.5 (#117)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
Berkeley Function Calling Leaderboard30.4%—
BALROG—7.8%

Reasoning Too close to call

Gemma 3 12B: 15.2 (#307), Qwen2.5 7B Instruct: 14.3 (#317)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
Chess Puzzles0%0%
DTBench48.8%47.7%
LMCA4.5%6.4%
Epoch Capabilities Index123.49118.44
CritPt0%—
LMArena Hard Prompts1309—

Math Gemma 3 12B leads

Gemma 3 12B: 21.0 (#273), Qwen2.5 7B Instruct: 11.8 (#300)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
OTIS Mock AIME 2024-202516.7%2.5%
Omni-MATH—29.4%
LMArena Math1307—

Knowledge Gemma 3 12B leads

Gemma 3 12B: 26.5 (#250), Qwen2.5 7B Instruct: 17.0 (#281)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
GPQA Diamond39.5%35.5%
MMLU-Pro—53.9%
Vectara Hallucination Rate4.4%—
GPQA (HELM)—34.1%
LMArena Expert1248—
MMLU—72.9%

Multimodal Not comparable

Gemma 3 12B: —, Qwen2.5 7B Instruct: —

BenchmarkGemma 3 12BQwen2.5 7B Instruct
MindCube46.7%—

Multilingual Not comparable

Gemma 3 12B: 45.9 (#160), Qwen2.5 7B Instruct: —

BenchmarkGemma 3 12BQwen2.5 7B Instruct
LMArena Non-English1318—
LMArena German1370—
LMArena Russian1335—

Instruction Following Gemma 3 12B leads

Gemma 3 12B: 68.8 (#179), Qwen2.5 7B Instruct: 63.4 (#226)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
IFEval—74.1%
LMArena Instruction Following1299—

Long Context Not comparable

Gemma 3 12B: 40.0 (#157), Qwen2.5 7B Instruct: —

BenchmarkGemma 3 12BQwen2.5 7B Instruct
LMArena Longer Query1317—

Writing & Preference Qwen2.5 7B Instruct leads

Gemma 3 12B: 47.7 (#205), Qwen2.5 7B Instruct: 48.8 (#194)

BenchmarkGemma 3 12BQwen2.5 7B Instruct
LMArena Text1334—
LMArena Creative Writing1331—
EQ-Bench Creative Writing1126—
WildBench—73.1%
LMArena Multi-Turn1334—

Frequently asked questions

Is Gemma 3 12B better than Qwen2.5 7B Instruct?

Gemma 3 12B is the stronger model overall, scoring 31.8 to 28.6 on the Noometry Index.

Which is cheaper, Gemma 3 12B or Qwen2.5 7B Instruct?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.

Is Gemma 3 12B or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 12B and Qwen2.5 7B Instruct share?

6 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper