BenchLeader
MiniMaxOpen weightsReasoning modelCompare with another model

MiniMax-M1

Quality#173 of 339
49.6Index
Below the median
−0.6 on the median
Price#134 of 255
$0.963per 1M tokens
Dearer than most
1.1× the median
Speed#187 of 216
40tokens/s
Bottom quarter
0.5× the median
Value#139 of 255
51.5points per $
Below the median
0.9× the median

Better value: Ling 3.0 Flash scores 51.7 for $0.115/M, 88% cheaper.

57 cheaper ranked models score higher: DeepSeek V4.1 Flash (58.5, $0.525), GPT-5.6 Luna (58.2, $0.450), Inkling 2 Small (57.9, $0.475) and 54 more.

As of 15 Nov 2026, MiniMax-M1 by MiniMax scores 49.6 on the BenchLeader Index (608 ranked configurations), with its best results in maths (54) and weakest in agents & tools (36). API pricing: $0.550 per 1M input tokens and $2.20 per 1M output tokens ($0.963 blended at 3:1), list price on 15 Nov 2026. It streams about 40 tokens/s (Artificial Analysis). Released 13 Jun 2025.

Key facts (as of 15 Nov 2026)

  • MiniMax-M1 API pricing: $0.550 per 1M input tokens and $2.20 per 1M output tokens ($0.963 blended at 3:1) (list price, 15 Nov 2026).
  • MiniMax-M1 streams about 40 tokens/s (Artificial Analysis, 15 Nov 2026).
  • MiniMax-M1 was released on 13 Jun 2025 (MiniMax).

In detail. MiniMax-M1 is a MiniMax open-weights reasoning model, released 13 Jun 2025. Its best configuration ranks #358 of 608 on the BenchLeader Index at 49.6 ±4.1, in the lower half. The ± is the point: 263 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in maths (54) and lowest in agents & tools (36). At $0.963 per million tokens blended it is mid-priced. Output speed of 40 tokens per second puts it in the slowest quarter, with a first answer in 4.2 s. Last measured 11 Nov 2026.

Blended price
$0.963/M
$0.550 in · $2.20 out
via Artificial Analysis
Output speed
40 tok/s
measured by Artificial Analysis
First answer
4.19 s
Context
1M
via Artificial Analysis
Full answer
84 s
last measured 13 Nov 2026
Cost per task
–
Tokens per task
–
Released
13 Jun 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index50
  2. Reasoning53
  3. Coding54
  4. Agents & tools36
  5. Maths54
  6. Instruction following44
  7. Human preference53
  8. Long context53

Embed this rank

More badge styles
[![MiniMax-M1 on BenchLeader: #171 overall](https://www.benchleader.com/badge/minimax-m1.svg?style=compact)](https://www.benchleader.com/models/minimax-m1)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when MiniMax ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

How its index has moved

9 Sep 2026 to 15 Nov 2026
454954

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
Arena Hard Prompts1381#195Arena (LMArena)
GPQA Diamond (AA)not in index69.7%#308Artificial Analysis
Humanity's Last Exam (AA)not in index8.9%#362Artificial Analysis
CritPtnot in index0.0%#337Artificial Analysis
Arena Expertnot in index1368#200Arena (LMArena)

Coding

Benchmarknot statedSourceTrend
Arena Coding1416#191Arena (LMArena)
LiveCodeBench (AA)not in index71.1%#60Artificial Analysis

Agents & tools

Benchmarknot statedSourceTrend
Terminal-Bench Hard3.0%#319Artificial Analysis
τ²-Bench Telecom (AA)not in index34.2%#247Artificial Analysis

Maths

Benchmarknot statedSourceTrend
Arena Maths1370#188Arena (LMArena)
AIME 2025 (AA)not in index61.0%#112Artificial Analysis

Instruction following

Benchmarknot statedSourceTrend
IFBench41.8%#247Artificial Analysis
Arena Instruction Followingnot in index1346#199Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1364#195Arena (LMArena)
Arena Creative Writingnot in index1319#203Arena (LMArena)
Arena Multi-turnnot in index1357#198Arena (LMArena)
Arena Longer Queriesnot in index1364#201Arena (LMArena)

Long context

Benchmarknot statedSourceTrend
Fiction.LiveBench 120k59.4%#18Fiction.live
AA-LCR v1.157.7%#309Artificial Analysis

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.2not in index11.7#356Artificial Analysis
AA Progress Index v1not in index218.5#355Artificial Analysis

Price history

The price above, per 1M tokens, every day it changed.

$0.00$0.605$1.21$1.82$2.42Sep 26Oct 26Nov 26
input output
Now $0.550 in · $2.20 out

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0009–11.7 s
Summarize a 30-page report12,000 / 600$0.0079–19.3 s
Code edit6,000 / 1,500$0.0066–41.9 s
Agentic coding session60,000 / 4,000$0.042–1.7 min
Structured extraction2,000 / 200$0.0015–9.2 s

More from MiniMax

New this month

See also

Embed or cite

Show where MiniMax-M1 ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![MiniMax-M1 on BenchLeader: #171 overall](https://www.benchleader.com/badge/minimax-m1.svg)](https://www.benchleader.com/models/minimax-m1)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 15). MiniMax-M1 on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 15, 2026, from https://www.benchleader.com/models/minimax-m1

BibTeX:

@misc{benchleader_minimax_m1_20261115,
  author       = {{BenchLeader}},
  title        = {{MiniMax-M1 on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/minimax-m1}},
  note         = {Data as of 2026-11-15}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are MiniMax-M1's benchmark scores?
As of 15 Nov 2026, MiniMax-M1 scores 49.6 ±4.1 on the BenchLeader Index, strongest in maths (54) and weakest in agents & tools (36). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does MiniMax-M1 rank?
MiniMax-M1 is #358 of 608 ranked configurations on 15 Nov 2026. 263 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
How much does MiniMax-M1 cost per 1M tokens?
As of 15 Nov 2026, MiniMax-M1 costs $0.550 per 1M input tokens and $2.20 per 1M output tokens, $0.963 blended (three input tokens per output token). The list price last changed on 9 Sep 2026.
When was MiniMax-M1 released?
MiniMax released MiniMax-M1 on 13 Jun 2025.

Data as of 15 Nov 2026. Compare with another model.

Cite as: BenchLeader, “MiniMax-M1: benchmarks, pricing, speed and rank”, data as of 15 Nov 2026, https://www.benchleader.com/models/minimax-m1.