Model comparison

Mistral Small 3.2 vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 31.2 on the Noometry Index.

Last verified October 12, 2026. 1 shared benchmarks.

Mistral Small 3.2

Mistral AI

31.2

Rank #280 Confirmed

Step 3

StepFun

40.5

Rank #149 Confirmed

Summary

They share 1 benchmark with published results for both. Mistral Small 3.2 scores higher in 0 categories and Step 3 in 4 categories; 4 gaps are clear of the uncertainty.
The widest gap is in math, where Step 3 leads 37.6 to 26.3.
The biggest single-benchmark swing is Kagi LLM Benchmark: 40.4% for Mistral Small 3.2 and 62.3% for Step 3.

Side by side

Mistral Small 3.2 and Step 3 specifications
	Mistral Small 3.2	Step 3
Provider	Mistral AI	StepFun
Noometry Index	31.2	40.5
Released	2025-06-20	—
Weights	Open	Open
Context window	256K	—
Max output	16K	—
Input $ / M tokens	$0.0938	—
Output $ / M tokens	$0.25	—
Results tracked	6	17

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

Category by category

Coding Not comparable

Mistral Small 3.2: —, Step 3: 40.1 (#147)

Coding benchmarks
Benchmark	Mistral Small 3.2	Step 3
LMArena Coding	—	1367

Reasoning Step 3 leads

Mistral Small 3.2: 18.1 (#287), Step 3: 28.4 (#105)

Reasoning benchmarks
Benchmark	Mistral Small 3.2	Step 3
Kagi LLM Benchmark	40.4%	62.3%
Chess Puzzles	1%	—
LMArena Hard Prompts	—	1355
Epoch Capabilities Index	131.74	—

Math Step 3 leads

Mistral Small 3.2: 26.3 (#260), Step 3: 37.6 (#148)

Math benchmarks
Benchmark	Mistral Small 3.2	Step 3
OTIS Mock AIME 2024-2025	30.3%	—
LMArena Math	—	1366

Knowledge Step 3 leads

Mistral Small 3.2: 26.7 (#256), Step 3: 36.8 (#164)

Knowledge benchmarks
Benchmark	Mistral Small 3.2	Step 3
GPQA Diamond	49.1%	—
LMArena Expert	—	1333

Multimodal Not comparable

Mistral Small 3.2: —, Step 3: 35.5 (#86)

Multimodal benchmarks
Benchmark	Mistral Small 3.2	Step 3
LMArena Vision	—	1177

Multilingual Not comparable

Mistral Small 3.2: —, Step 3: 46.3 (#159)

Multilingual benchmarks
Benchmark	Mistral Small 3.2	Step 3
LMArena Non-English	—	1327
LMArena Chinese	—	1397
LMArena German	—	1371
LMArena Korean	—	1269
LMArena Russian	—	1331
LMArena Spanish	—	1371

Instruction Following Not comparable

Mistral Small 3.2: —, Step 3: 70.4 (#164)

Instruction Following benchmarks
Benchmark	Mistral Small 3.2	Step 3
LMArena Instruction Following	—	1332

Long Context Not comparable

Mistral Small 3.2: —, Step 3: 40.3 (#157)

Long Context benchmarks
Benchmark	Mistral Small 3.2	Step 3
LMArena Longer Query	—	1326

Writing & Preference Step 3 leads

Mistral Small 3.2: 45.0 (#224), Step 3: 54.3 (#151)

Writing & Preference benchmarks
Benchmark	Mistral Small 3.2	Step 3
LMArena Text	—	1350
LMArena Creative Writing	—	1321
EQ-Bench Creative Writing	1255	—
LMArena Multi-Turn	—	1341

Frequently asked questions

Is Mistral Small 3.2 better than Step 3?