Model comparison

Mistral Medium 3.1 vs Step 3

Step 3 is the stronger model overall, scoring 39.9 to 31.5 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Mistral Medium 3.1

Mistral AI

31.5

Rank #260 Reported

Step 3

StepFun

39.9

Rank #145 Confirmed

Summary

The widest gap is in reasoning, where Step 3 leads 27.6 to 10.1.
Step 3 has downloadable open weights; the other is API-only.

Side by side

Mistral Medium 3.1 and Step 3 specifications
	Mistral Medium 3.1	Step 3
Provider	Mistral AI	StepFun
Noometry Index	31.5	39.9
Released	—	—
Weights	Proprietary	Open
Context window	131K	—
Max output	105K	—
Input $ / M tokens	$0.40	—
Output $ / M tokens	$2	—
Results tracked	3	17

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

Category by category

Coding Not comparable

Mistral Medium 3.1: —, Step 3: 39.5 (#144)

Coding benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Coding	—	1367

Reasoning Step 3 leads

Mistral Medium 3.1: 10.1 (#336), Step 3: 27.6 (#102)

Reasoning benchmarks
Benchmark	Mistral Medium 3.1	Step 3
Kagi LLM Benchmark	—	62.3%
NYT Connections (extended)	6.5%	—
Thematic Generalization	20.3%	—
LMArena Hard Prompts	—	1355

Math Not comparable

Mistral Medium 3.1: —, Step 3: 34.9 (#148)

Math benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Math	—	1366

Knowledge Not comparable

Mistral Medium 3.1: —, Step 3: 36.2 (#161)

Knowledge benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Expert	—	1333

Multimodal Not comparable

Mistral Medium 3.1: —, Step 3: 34.9 (#81)

Multimodal benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Vision	—	1176

Multilingual Not comparable

Mistral Medium 3.1: —, Step 3: 46.5 (#154)

Multilingual benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Non-English	—	1327
LMArena Chinese	—	1396
LMArena German	—	1371
LMArena Korean	—	1271
LMArena Russian	—	1331
LMArena Spanish	—	1372

Instruction Following Not comparable

Mistral Medium 3.1: —, Step 3: 70.6 (#159)

Instruction Following benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Instruction Following	—	1332

Long Context Not comparable

Mistral Medium 3.1: —, Step 3: 40.3 (#152)

Long Context benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Longer Query	—	1326

Writing & Preference Mistral Medium 3.1 leads

Mistral Medium 3.1: 55.6 (#140), Step 3: 54.5 (#146)

Writing & Preference benchmarks
Benchmark	Mistral Medium 3.1	Step 3
LMArena Text	—	1351
LMArena Creative Writing	—	1322
EQ-Bench Creative Writing	1476	—
LMArena Multi-Turn	—	1340

Frequently asked questions

Is Mistral Medium 3.1 better than Step 3?