Noometry

Model comparison

Gemma 2 9B vs Qwen2.5 7B Instruct

Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 25.9 on the Noometry Index.

Last verified . 6 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • They share 6 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and Qwen2.5 7B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 32.1.
  • The biggest single-benchmark swing is GPQA Diamond: 27.5% for Gemma 2 9B and 35.5% for Qwen2.5 7B Instruct.

Side by side

Gemma 2 9BQwen2.5 7B Instruct
ProviderGoogleAlibaba (Qwen)
Noometry Index25.929.0
Released2024-06-242024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.17
Output $ / M tokens—$0.70
Results tracked3515

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

Category by category

Coding Qwen2.5 7B Instruct leads

Gemma 2 9B: 29.4 (#304), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
BigCodeBench Instruct34.7%37.6%
BigCodeBench Complete40.6%46.1%
LiveBench Coding22.5%—
LMArena Coding1173—

Agentic & Tool Use Not comparable

Gemma 2 9B: —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
BALROG—7.8%

Reasoning Gemma 2 9B leads

Gemma 2 9B: 15.9 (#309), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
Epoch Capabilities Index119.83118.51
Chess Puzzles—0%
LiveBench Reasoning15.2%—
LMArena Hard Prompts1171—
DTBench—47.7%
LiveBench Data Analysis36.4%—
LMCA—6.4%
LiveBench28.7%—
PIQA83.7%—

Math Qwen2.5 7B Instruct leads

Gemma 2 9B: 9.9 (#318), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
OTIS Mock AIME 2024-20250.6%2.5%
Omni-MATH—29.4%
LiveBench Math19.8%—
LMArena Math1183—
MATH Level 521%—
GSM8K84.9%—

Knowledge Qwen2.5 7B Instruct leads

Gemma 2 9B: 9.7 (#305), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
GPQA Diamond27.5%35.5%
MMLU72.1%72.9%
MMLU-Pro—53.9%
GPQA (HELM)—34.1%
LMArena Expert1147—
BoolQ85.7%—

Multilingual Not comparable

Gemma 2 9B: 36.6 (#238), Qwen2.5 7B Instruct: —

BenchmarkGemma 2 9BQwen2.5 7B Instruct
LMArena Non-English1188—
LMArena Chinese1185—
LMArena French1190—
LMArena German1186—
LMArena Japanese1144—
LMArena Korean1137—
LMArena Russian1200—
LMArena Spanish1200—

Instruction Following Qwen2.5 7B Instruct leads

Gemma 2 9B: 57.6 (#269), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
LiveBench Instruction Following52.6%—
IFEval—74.1%
LMArena Instruction Following1178—

Long Context Not comparable

Gemma 2 9B: 36.3 (#233), Qwen2.5 7B Instruct: —

BenchmarkGemma 2 9BQwen2.5 7B Instruct
LMArena Longer Query1197—

Writing & Preference Qwen2.5 7B Instruct leads

Gemma 2 9B: 32.1 (#281), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkGemma 2 9BQwen2.5 7B Instruct
LMArena Text1207—
LMArena Creative Writing1206—
EQ-Bench Creative Writing841—
WildBench—73.1%
LMArena Multi-Turn1193—
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Qwen2.5 7B Instruct share?

6 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper