Model comparison

Grok 4.20 (Non-Reasoning) vs MiniMax-M2.5

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 3.0× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Last verified October 11, 2026. 30 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

MiniMax-M2.5

MiniMax

38.3

Rank #188 Confirmed

Summary

They share 30 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and MiniMax-M2.5 in 1 category; 9 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 17.5.
The biggest single-benchmark swing is NYT Connections (extended): 85.4% for Grok 4.20 (Non-Reasoning) and 16.8% for MiniMax-M2.5.
MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 205K.
MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning) and MiniMax-M2.5 specifications
	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
Provider	xAI	MiniMax
Noometry Index	48.6	38.3
Released	2026-02-17	2026-02-12
Weights	Proprietary	Open
Context window	1M	205K
Max output	30K	131K
Input $ / M tokens	$1.25	$0.30
Output $ / M tokens	$2.50	$1.20
Results tracked	46	33

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

Category by category

Coding MiniMax-M2.5 leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), MiniMax-M2.5: 48.1 (#58)

Coding benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
LMArena WebDev	1375	1387
LMArena Coding	1459	1381
ALE-Bench	1,150	618.17
SWE-bench Verified (bash only)	—	75.8%
SWE-bench Multilingual	—	68.3%
WeirdML	52.3%	—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 34.4 (#46), MiniMax-M2.5: 30.4 (#77)

Agentic & Tool Use benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
Terminal-Bench	57.3%	42.7%
Vending-Bench 2	4,663	-23.16
τ²-bench Banking	18%	—
LMArena Search	1189	—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), MiniMax-M2.5: 17.5 (#292)

Reasoning benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
ARC-AGI-2	65.1%	4.9%
Kagi LLM Benchmark	75%	55.2%
NYT Connections (extended)	85.4%	16.8%
ARC-AGI-1	89.5%	63.7%
LMArena Hard Prompts	1451	1372
Epoch Capabilities Index	151.98	146.68
Chess Puzzles	24%	—
Thematic Generalization	63.8%	—
DTBench	90.1%	—
LMCA	38.7%	—
ForecastBench	61.4	—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), MiniMax-M2.5: 26.9 (#253)

Math benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
ProofBench	14%	4%
LMArena Math	1455	1378
FrontierMath (Tiers 1-3)	44.9%	—
FrontierMath Tier 4	17.1%	—
OTIS Mock AIME 2024-2025	92.2%	—

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), MiniMax-M2.5: 39.2 (#135)

Knowledge benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
LMArena Expert	1439	1379
GPQA Diamond	89.3%	—
SimpleQA Verified	30.2%	—
Vectara Hallucination Rate	—	9.1%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), MiniMax-M2.5: —

Multimodal benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
LMArena Vision	1263	—
Blueprint-Bench 2	0%	—
LMArena Document	1416	—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), MiniMax-M2.5: 47.1 (#152)

Multilingual benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
LMArena Non-English	1441	1338
LMArena Chinese	1481	1393
LMArena French	1476	1362
LMArena German	1465	1362
LMArena Japanese	1449	1171
LMArena Korean	1417	1232
LMArena Russian	1458	1358
LMArena Spanish	1443	1354

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), MiniMax-M2.5: 71.5 (#148)

Instruction Following benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
LMArena Instruction Following	1420	1353

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), MiniMax-M2.5: 37.5 (#216)

Long Context benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
CL-bench	22.2%	11.4%
CL-bench Life	11.9%	6.3%
LMArena Longer Query	1437	1366

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), MiniMax-M2.5: 53.9 (#153)

Writing & Preference benchmarks
Benchmark	Grok 4.20 (Non-Reasoning)	MiniMax-M2.5
LMArena Text	1451	1359
LMArena Creative Writing	1438	1331
EQ-Bench Creative Writing	1574	1361
LMArena Multi-Turn	1456	1364

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than MiniMax-M2.5?

Which is cheaper, Grok 4.20 (Non-Reasoning) or MiniMax-M2.5?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 205K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and MiniMax-M2.5 share?

30 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and MiniMax-M2.5 has 33.