Noometry

MiniMax, open weights

MiniMax M1

MiniMax M1 by MiniMax ranks 150th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.3. Its strongest category is reasoning, where it ranks 126th. API pricing starts at $0.55 per million input tokens and $2.20 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#150 of 354
Index score
40.3
Evidence
Confirmed 18 results
Provider
MiniMax
Released
June 13, 2025
Weights
Open weights
Reasoning
Yes
Context window
1M
Max output
40K
Input price
$0.55 / M
Output price
$2.20 / M
Blended price
$0.96 / M
Output speed
Not measured
Value
#111 of 219
Knowledge cutoff
Unknown
Input
text

Category scores

Each category score combines every public result we have in that category.

  1. Coding 39.9
  2. Reasoning 26.9
  3. Math 37.5
  4. Knowledge 36.4
  5. Multilingual 45.8
  6. Instruction Following 69.3
  7. Long Context 41.4
  8. Writing & Preference 53.1
CategoryScoreRankResults
Coding39.9#1531
Reasoning26.9#1261
Math37.5#1511
Knowledge36.4#1701
Multilingual45.8#1631
Instruction Following69.3#1741
Long Context41.4#1412
Writing & Preference53.1#1613

Strengths and weaknesses

Categories where MiniMax M1 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Reasoning26.9+3.3#126 of 350, top 36%
Coding39.9+1.1#153 of 340, top 45%
Math37.5+1.0#151 of 327, top 47%

Weakest categories

CategoryScorevs medianRank
Instruction Following69.3−2.0#174 of 305, top 58%
Multilingual45.8−1.6#163 of 297, top 55%
Knowledge36.4−1.0#170 of 314, top 55%

Closest competitors

The models ranked just above and below MiniMax M1. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Qwen2.5-Max#14640.7——Compare
Nemotron 3 Nano 30B A3B#14740.6$0.0875—Compare
Granite 4.2 8B#14840.5$0.11—Compare
Step 3#14940.5—7Compare
Nvidia Llama 3.3 Nemotron Super 49b v1.5#15140.3$0.40—Compare
Mistral Medium 3.5#15240.2$350Compare
Nemotron 3 Super#15340.1$0.17—Compare
Llama 3.3 Nemotron 49b Super v1#15440.1——Compare

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

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
LMArena Coding1359#169 of 294, top 58%LMArena2026-10-08

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1339#165 of 297, top 56%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1361#155 of 285, top 55%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1317#170 of 273, top 63%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1319#163 of 297, top 55%LMArena2026-10-08
LMArena Chinese1360#160 of 285, top 57%LMArena2026-10-08
LMArena French1370#135 of 223, top 61%LMArena2026-10-08
LMArena German1350#130 of 231, top 57%LMArena2026-10-08
LMArena Japanese1217#149 of 211, top 71%LMArena2026-10-08
LMArena Korean1266#143 of 213, top 68%LMArena2026-10-08
LMArena Russian1329#161 of 283, top 57%LMArena2026-10-08
LMArena Spanish1353#143 of 226, top 64%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1312#166 of 298, top 56%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
Fiction.LiveBench69.4%#18 of 47, top 39%Epoch AI
LMArena Longer Query1326#167 of 291, top 58%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1343#161 of 297, top 55%LMArena2026-10-08
LMArena Creative Writing1298#166 of 295, top 57%LMArena2026-10-08
LMArena Multi-Turn1335#168 of 295, top 57%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
openrouter$0.55$2.20—2026-10-10

All MiniMax API prices → Estimate your cost →

Compare MiniMax M1

Other MiniMax models

Frequently asked questions

How good is MiniMax M1?

MiniMax M1 by MiniMax ranks 150th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.3. Its strongest category is reasoning, where it ranks 126th. API pricing starts at $0.55 per million input tokens and $2.20 per million output tokens, with a 1M-token context window.

How much does MiniMax M1 cost?

MiniMax M1 costs $0.55 per million input tokens and $2.20 per million output tokens on openrouter.

What is MiniMax M1's context window?

MiniMax M1 accepts up to 1M tokens of input and can write up to 40K tokens in one response.

Is MiniMax M1 open source?

Yes. MiniMax M1's weights are downloadable; check the license for commercial terms.

What are MiniMax M1's strengths and weaknesses?

Relative to other ranked models, MiniMax M1 places best in reasoning, coding, math and lowest in instruction following, multilingual, knowledge.

What is MiniMax M1 best at?

Its best category is reasoning, where it ranks 126th on Noometry.