Model comparison

MiniMax-M2.5 vs Mistral Large

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.9 on the Noometry Index.

Last verified October 11, 2026. 21 shared benchmarks.

MiniMax-M2.5

MiniMax

38.3

Rank #188 Confirmed

Mistral Large

Mistral AI

31.9

Rank #263 Confirmed

Summary

They share 21 benchmarks with published results for both. MiniMax-M2.5 scores higher in 8 categories and Mistral Large in 1 category; 8 gaps are clear of the uncertainty.
The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 34.3.
MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Mistral Large.
MiniMax-M2.5 accepts more context: 205K tokens versus 131K.

Side by side

MiniMax-M2.5 and Mistral Large specifications
	MiniMax-M2.5	Mistral Large
Provider	MiniMax	Mistral AI
Noometry Index	38.3	31.9
Released	2026-02-12	2024-02-26
Weights	Open	Open
Context window	205K	131K
Max output	131K	16K
Input $ / M tokens	$0.30	$2
Output $ / M tokens	$1.20	$6
Results tracked	33	51

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 Large: 34.3 (#240)

Coding benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Coding	1381	1277
ALE-Bench	618.17	264.7
SWE-bench Verified (bash only)	75.8%	—
LMArena WebDev	1387	—
SWE-bench Multilingual	68.3%	—
SciCode	—	36.2%
BigCodeBench Instruct	—	30%
LiveBench Coding	—	47.1%
BigCodeBench Complete	—	38.3%
HumanEval+	—	62.2%
MBPP+	—	59.5%

Agentic & Tool Use MiniMax-M2.5 leads

MiniMax-M2.5: 30.4 (#77), Mistral Large: 28.6 (#89)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
Terminal-Bench	42.7%	—
Berkeley Function Calling Leaderboard	—	38.4%
Vending-Bench 2	-23.16	—

Reasoning MiniMax-M2.5 leads

MiniMax-M2.5: 17.5 (#292), Mistral Large: 15.8 (#310)

Reasoning benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Hard Prompts	1372	1257
Epoch Capabilities Index	146.68	128.52
ARC-AGI-2	4.9%	—
SimpleBench	—	22.5%
Kagi LLM Benchmark	55.2%	—
NYT Connections (extended)	16.8%	—
ARC-AGI-1	63.7%	—
CritPt	—	0%
LiveBench Reasoning	—	43.5%
DTBench	—	65.1%
LiveBench Data Analysis	—	50.1%
LMCA	—	16.7%
ForecastBench	—	57.1
LiveBench	—	48.4%

Math MiniMax-M2.5 leads

MiniMax-M2.5: 26.9 (#253), Mistral Large: 18.2 (#291)

Math benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Math	1378	1262
OTIS Mock AIME 2024-2025	—	8.5%
ProofBench	4%	—
Omni-MATH	—	28.1%
LiveBench Math	—	42.5%
MATH Level 5	—	50.3%
FrontierMath (Feb 2025 set)	—	0.3%

Knowledge MiniMax-M2.5 leads

MiniMax-M2.5: 39.2 (#135), Mistral Large: 30.1 (#230)

Knowledge benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
Vectara Hallucination Rate	9.1%	4.5%
LMArena Expert	1379	1232
GPQA Diamond	—	51.3%
MMLU-Pro	—	59.9%
Confabulations	—	21.4%
GPQA (HELM)	—	43.5%
MMLU	—	80%

Multilingual MiniMax-M2.5 leads

MiniMax-M2.5: 47.1 (#152), Mistral Large: 40.0 (#219)

Multilingual benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Non-English	1338	1237
LMArena Chinese	1393	1240
LMArena French	1362	1325
LMArena German	1362	1254
LMArena Japanese	1171	1188
LMArena Korean	1232	1202
LMArena Russian	1358	1257
LMArena Spanish	1354	1268

Instruction Following MiniMax-M2.5 leads

MiniMax-M2.5: 71.5 (#148), Mistral Large: 67.9 (#191)

Instruction Following benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Instruction Following	1353	1249
LiveBench Instruction Following	—	67.9%
IFEval	—	87.7%

Long Context Too close to call

MiniMax-M2.5: 37.5 (#216), Mistral Large: 38.3 (#199)

Long Context benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Longer Query	1366	1261
CL-bench	11.4%	—
CL-bench Life	6.3%	—

Writing & Preference MiniMax-M2.5 leads

MiniMax-M2.5: 53.9 (#153), Mistral Large: 40.7 (#242)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.5	Mistral Large
LMArena Text	1359	1266
LMArena Creative Writing	1331	1243
EQ-Bench Creative Writing	1361	985
LMArena Multi-Turn	1364	1260
Short-Story Creative Writing	—	69%
WildBench	—	80.1%
LiveBench Language	—	39.4%

Frequently asked questions

Is MiniMax-M2.5 better than Mistral Large?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.9 on the Noometry Index.

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

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Mistral Large lists at $2 and $6.

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

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 34.3 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 131K.

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

21 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Mistral Large has 51.