Model comparison

MiniMax-M2.5 vs Mistral Small 3.1

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.7 on the Noometry Index.

Last verified October 10, 2026. 19 shared benchmarks.

MiniMax-M2.5

MiniMax

38.3

Rank #188 Confirmed

Mistral Small 3.1

Mistral AI

31.7

Rank #269 Confirmed

Summary

They share 19 benchmarks with published results for both. MiniMax-M2.5 scores higher in 6 categories and Mistral Small 3.1 in 2 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax-M2.5 leads 53.9 to 37.0.
Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
MiniMax-M2.5 accepts more context: 205K tokens versus 128K.

Side by side

MiniMax-M2.5 and Mistral Small 3.1 specifications
	MiniMax-M2.5	Mistral Small 3.1
Provider	MiniMax	Mistral AI
Noometry Index	38.3	31.7
Released	2026-02-12	2025-03-17
Weights	Open	Open
Context window	205K	128K
Max output	131K	102K
Input $ / M tokens	$0.30	$0.35
Output $ / M tokens	$1.20	$0.56
Results tracked	33	28

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.5: 48.1 (#58), Mistral Small 3.1: 38.3 (#179)

Coding benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Coding	1381	1309
SWE-bench Verified (bash only)	75.8%	—
LMArena WebDev	1387	—
SWE-bench Multilingual	68.3%	—
ALE-Bench	618.17	—

Agentic & Tool Use Not comparable

MiniMax-M2.5: 30.4 (#77), Mistral Small 3.1: —

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
Terminal-Bench	42.7%	—
Vending-Bench 2	-23.16	—

Reasoning Mistral Small 3.1 leads

MiniMax-M2.5: 17.5 (#292), Mistral Small 3.1: 19.7 (#254)

Reasoning benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Hard Prompts	1372	1278
Epoch Capabilities Index	146.68	127.48
ARC-AGI-2	4.9%	—
Kagi LLM Benchmark	55.2%	—
NYT Connections (extended)	16.8%	—
ARC-AGI-1	63.7%	—
Chess Puzzles	—	1%

Math MiniMax-M2.5 leads

MiniMax-M2.5: 26.9 (#253), Mistral Small 3.1: 14.7 (#301)

Math benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Math	1378	1262
OTIS Mock AIME 2024-2025	—	3.9%
ProofBench	4%	—
Omni-MATH	—	24.8%

Knowledge MiniMax-M2.5 leads

MiniMax-M2.5: 39.2 (#135), Mistral Small 3.1: 22.6 (#271)

Knowledge benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Expert	1379	1257
GPQA Diamond	—	41.9%
MMLU-Pro	—	61%
Vectara Hallucination Rate	9.1%	—
GPQA (HELM)	—	39.2%

Multimodal Not comparable

MiniMax-M2.5: —, Mistral Small 3.1: 33.2 (#99)

Multimodal benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Vision	—	1136

Multilingual MiniMax-M2.5 leads

MiniMax-M2.5: 47.1 (#152), Mistral Small 3.1: 41.2 (#209)

Multilingual benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Non-English	1338	1255
LMArena Chinese	1393	1253
LMArena French	1362	1273
LMArena German	1362	1266
LMArena Japanese	1171	1208
LMArena Korean	1232	1206
LMArena Russian	1358	1263
LMArena Spanish	1354	1283

Instruction Following MiniMax-M2.5 leads

MiniMax-M2.5: 71.5 (#148), Mistral Small 3.1: 63.6 (#230)

Instruction Following benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Instruction Following	1353	1264
IFEval	—	75%

Long Context Mistral Small 3.1 leads

MiniMax-M2.5: 37.5 (#216), Mistral Small 3.1: 39.5 (#178)

Long Context benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Longer Query	1366	1299
CL-bench	11.4%	—
CL-bench Life	6.3%	—

Writing & Preference MiniMax-M2.5 leads

MiniMax-M2.5: 53.9 (#153), Mistral Small 3.1: 37.0 (#259)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.5	Mistral Small 3.1
LMArena Text	1359	1277
LMArena Creative Writing	1331	1253
EQ-Bench Creative Writing	1361	761
LMArena Multi-Turn	1364	1270
WildBench	—	78.8%

Frequently asked questions

Is MiniMax-M2.5 better than Mistral Small 3.1?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.7 on the Noometry Index.

Which is cheaper, MiniMax-M2.5 or Mistral Small 3.1?

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.

Is MiniMax-M2.5 or Mistral Small 3.1 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 38.3 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 128K.

How many benchmarks do MiniMax-M2.5 and Mistral Small 3.1 share?

19 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Mistral Small 3.1 has 28.