Model comparison

MiniMax-M2.7 vs o1

o1 is the stronger model overall, scoring 40.9 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 50× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

Last verified October 11, 2026. 19 shared benchmarks.

MiniMax-M2.7

MiniMax

37.7

Rank #196 Confirmed

o1 OpenAI

40.9

Rank #143 Confirmed

Summary

They share 19 benchmarks with published results for both. MiniMax-M2.7 scores higher in 3 categories and o1 in 6 categories; 7 gaps are clear of the uncertainty.
The widest gap is in math, where o1 leads 36.1 to 25.9.
The biggest single-benchmark swing is WeirdML: 37% for MiniMax-M2.7 and 47.6% for o1.
MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $15 / $60 for o1.
MiniMax-M2.7 accepts more context: 205K tokens versus 200K.
MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M2.7 and o1 specifications
	MiniMax-M2.7	o1
Provider	MiniMax	OpenAI
Noometry Index	37.7	40.9
Released	2026-03-18	2024-09-12
Weights	Open	Proprietary
Context window	205K	200K
Max output	131K	100K
Input $ / M tokens	$0.30	$15
Output $ / M tokens	$1.20	$60
Results tracked	30	52

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

Category by category

Coding o1 leads

MiniMax-M2.7: 41.8 (#120), o1: 46.1 (#70)

Coding benchmarks
Benchmark	MiniMax-M2.7	o1
WeirdML	37%	47.6%
LMArena Coding	1454	1367
Aider Polyglot	—	61.7%
LMArena WebDev	1398	—
SciCode	47%	—
LiveBench Coding	—	69.7%
CadEval	—	56%
ALE-Bench	599.25	—
HumanEval+	—	89%
MBPP+	—	80.2%

Agentic & Tool Use Too close to call

MiniMax-M2.7: 25.1 (#111), o1: 24.6 (#117)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.7	o1
Terminal-Bench	45.1%	—
Cybench	—	10%
ExploitBench	13.3%	—
GBAEval	0%	—
METR Time Horizons	—	51.1%

Reasoning o1 leads

MiniMax-M2.7: 19.7 (#253), o1: 27.9 (#111)

Reasoning benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Hard Prompts	1422	1371
Epoch Capabilities Index	145.85	141.91
SimpleBench	—	41.7%
NYT Connections (extended)	24.7%	—
ARC-AGI-1	—	30.7%
CritPt	0.6%	—
Chess Puzzles	—	15%
EnigmaEval	—	5.7%
Thematic Generalization	39.3%	—
LiveBench Reasoning	—	91.6%
DTBench	—	74.7%
LiveBench Data Analysis	—	65.5%
LMCA	—	22.3%
LiveBench	—	75.7%

Math o1 leads

MiniMax-M2.7: 25.9 (#263), o1: 36.1 (#175)

Math benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Math	1420	1388
FrontierMath (Tiers 1-3)	—	14.7%
OTIS Mock AIME 2024-2025	—	73.3%
ProofBench	3%	—
LiveBench Math	—	80.3%
MATH Level 5	—	94.7%
FrontierMath (Feb 2025 set)	—	9.3%

Knowledge o1 leads

MiniMax-M2.7: 37.7 (#152), o1: 41.5 (#110)

Knowledge benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Expert	1444	1361
GPQA Diamond	—	76.8%
Humanity's Last Exam	—	8%
SimpleQA Verified	—	41.1%
Confabulations	—	11.7%
Vectara Hallucination Rate	12.9%	—

Multimodal Not comparable

MiniMax-M2.7: —, o1: 34.2 (#93)

Multimodal benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Vision	—	1168
GeoBench	—	80%
VPCT	—	37%
SpatialViz-Bench	—	41.4%

Multilingual MiniMax-M2.7 leads

MiniMax-M2.7: 50.3 (#123), o1: 48.6 (#142)

Multilingual benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Non-English	1382	1358
LMArena Chinese	1441	1394
LMArena French	1421	1344
LMArena German	1398	1337
LMArena Japanese	1262	1346
LMArena Korean	1313	1396
LMArena Russian	1383	1356
LMArena Spanish	1403	1345

Instruction Following Too close to call

MiniMax-M2.7: 74.1 (#103), o1: 74.8 (#86)

Instruction Following benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Instruction Following	1405	1367
LiveBench Instruction Following	—	81.5%

Long Context o1 leads

MiniMax-M2.7: 43.3 (#99), o1: 50.3 (#9)

Long Context benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Longer Query	1419	1378
Fiction.LiveBench	—	83.3%

Writing & Preference MiniMax-M2.7 leads

MiniMax-M2.7: 58.9 (#112), o1: 55.6 (#144)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.7	o1
LMArena Text	1405	1366
LMArena Creative Writing	1354	1348
LMArena Multi-Turn	1412	1369
Short-Story Creative Writing	—	70.2%
LiveBench Language	—	65.4%

Frequently asked questions

Is MiniMax-M2.7 better than o1?

o1 is the stronger model overall, scoring 40.9 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 50× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

Which is cheaper, MiniMax-M2.7 or o1?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; o1 lists at $15 and $60.

Is MiniMax-M2.7 or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 200K.

How many benchmarks do MiniMax-M2.7 and o1 share?

19 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and o1 has 52.