Noometry

Model comparison

Gemma 2 9B vs Mistral Small 3.1

Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 25.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Mistral Small 3.1 Mistral AI

31.7

Rank #269 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Mistral Small 3.1 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Small 3.1 leads 22.6 to 9.7.
  • The biggest single-benchmark swing is GPQA Diamond: 27.5% for Gemma 2 9B and 41.9% for Mistral Small 3.1.

Side by side

Gemma 2 9BMistral Small 3.1
ProviderGoogleMistral AI
Noometry Index25.931.7
Released2024-06-242025-03-17
WeightsOpenOpen
Context window—128K
Max output—102K
Input $ / M tokens—$0.35
Output $ / M tokens—$0.56
Results tracked3528

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

Category by category

Coding Mistral Small 3.1 leads

Gemma 2 9B: 29.4 (#304), Mistral Small 3.1: 38.3 (#179)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Coding11731309
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—

Reasoning Mistral Small 3.1 leads

Gemma 2 9B: 15.9 (#309), Mistral Small 3.1: 19.7 (#254)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Hard Prompts11711278
Epoch Capabilities Index119.83127.48
Chess Puzzles—1%
LiveBench Reasoning15.2%—
LiveBench Data Analysis36.4%—
LiveBench28.7%—
PIQA83.7%—

Math Mistral Small 3.1 leads

Gemma 2 9B: 9.9 (#318), Mistral Small 3.1: 14.7 (#301)

BenchmarkGemma 2 9BMistral Small 3.1
OTIS Mock AIME 2024-20250.6%3.9%
LMArena Math11831262
Omni-MATH—24.8%
LiveBench Math19.8%—
MATH Level 521%—
GSM8K84.9%—

Knowledge Mistral Small 3.1 leads

Gemma 2 9B: 9.7 (#305), Mistral Small 3.1: 22.6 (#271)

BenchmarkGemma 2 9BMistral Small 3.1
GPQA Diamond27.5%41.9%
LMArena Expert11471257
MMLU-Pro—61%
GPQA (HELM)—39.2%
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, Mistral Small 3.1: 33.2 (#99)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Vision—1136

Multilingual Mistral Small 3.1 leads

Gemma 2 9B: 36.6 (#238), Mistral Small 3.1: 41.2 (#209)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Non-English11881255
LMArena Chinese11851253
LMArena French11901273
LMArena German11861266
LMArena Japanese11441208
LMArena Korean11371206
LMArena Russian12001263
LMArena Spanish12001283

Instruction Following Mistral Small 3.1 leads

Gemma 2 9B: 57.6 (#269), Mistral Small 3.1: 63.6 (#230)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Instruction Following11781264
LiveBench Instruction Following52.6%—
IFEval—75%

Long Context Mistral Small 3.1 leads

Gemma 2 9B: 36.3 (#233), Mistral Small 3.1: 39.5 (#178)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Longer Query11971299

Writing & Preference Mistral Small 3.1 leads

Gemma 2 9B: 32.1 (#281), Mistral Small 3.1: 37.0 (#259)

BenchmarkGemma 2 9BMistral Small 3.1
LMArena Text12071277
LMArena Creative Writing12061253
EQ-Bench Creative Writing841761
LMArena Multi-Turn11931270
WildBench—78.8%
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than Mistral Small 3.1?

Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 25.9 on the Noometry Index.

Is Gemma 2 9B or Mistral Small 3.1 better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and Mistral Small 3.1 share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Mistral Small 3.1 has 28.

Related comparisons

Go deeper