Model comparison

Llama 3.2 90B vs MiniMax-M2.5

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 27.5 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

Summary

They share 1 benchmark with published results for both. Llama 3.2 90B scores higher in 1 category and MiniMax-M2.5 in 3 categories; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where MiniMax-M2.5 leads 39.2 to 21.7.

Side by side

Llama 3.2 90B and MiniMax-M2.5 specifications
	Llama 3.2 90B	MiniMax-M2.5
Provider	Meta	MiniMax
Noometry Index	27.5	38.3
Released	2024-09-24	2026-02-12
Weights	Open	Open
Context window	—	205K
Max output	—	131K
Input $ / M tokens	—	$0.30
Output $ / M tokens	—	$1.20
Results tracked	9	33

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, MiniMax-M2.5: 48.1 (#58)

Coding benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
SWE-bench Verified (bash only)	—	75.8%
LMArena WebDev	—	1387
SWE-bench Multilingual	—	68.3%
LMArena Coding	—	1381
ALE-Bench	—	618.17

Agentic & Tool Use Too close to call

Llama 3.2 90B: 30.0 (#80), MiniMax-M2.5: 30.4 (#77)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
Terminal-Bench	—	42.7%
BALROG	27.3%	—
Vending-Bench 2	—	-23.16

Reasoning Llama 3.2 90B leads

Llama 3.2 90B: 21.7 (#217), MiniMax-M2.5: 17.5 (#292)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
Epoch Capabilities Index	125.5	146.68
ARC-AGI-2	—	4.9%
Kagi LLM Benchmark	—	55.2%
NYT Connections (extended)	—	16.8%
ARC-AGI-1	—	63.7%
EnigmaEval	0.4%	—
LMArena Hard Prompts	—	1372

Math MiniMax-M2.5 leads

Llama 3.2 90B: 11.1 (#308), MiniMax-M2.5: 26.9 (#253)

Math benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
OTIS Mock AIME 2024-2025	2.6%	—
ProofBench	—	4%
LMArena Math	—	1378
MATH Level 5	39.4%	—

Knowledge MiniMax-M2.5 leads

Llama 3.2 90B: 21.7 (#274), MiniMax-M2.5: 39.2 (#135)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
GPQA Diamond	41%	—
Vectara Hallucination Rate	—	9.1%
LMArena Expert	—	1379
MMLU	80.3%	—

Multimodal Not comparable

Llama 3.2 90B: 25.4 (#124), MiniMax-M2.5: —

Multimodal benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
LMArena Vision	1000	—
GeoBench	52%	—

Multilingual Not comparable

Llama 3.2 90B: —, MiniMax-M2.5: 47.1 (#152)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
LMArena Non-English	—	1338
LMArena Chinese	—	1393
LMArena French	—	1362
LMArena German	—	1362
LMArena Japanese	—	1171
LMArena Korean	—	1232
LMArena Russian	—	1358
LMArena Spanish	—	1354

Instruction Following Not comparable

Llama 3.2 90B: —, MiniMax-M2.5: 71.5 (#148)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
LMArena Instruction Following	—	1353

Long Context Not comparable

Llama 3.2 90B: —, MiniMax-M2.5: 37.5 (#216)

Long Context benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
CL-bench	—	11.4%
CL-bench Life	—	6.3%
LMArena Longer Query	—	1366

Writing & Preference Not comparable

Llama 3.2 90B: —, MiniMax-M2.5: 53.9 (#153)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	MiniMax-M2.5
LMArena Text	—	1359
LMArena Creative Writing	—	1331
EQ-Bench Creative Writing	—	1361
LMArena Multi-Turn	—	1364

Frequently asked questions

Is Llama 3.2 90B better than MiniMax-M2.5?