Skip to content
fedi.software

MiniMax M1 in fedi-index

The score in every slice, what it is made of, value, local run and history.

fedi-index · General

C 1,321 ±2

Percentile 39 · #179 · provisional

People prefer / Solves tasks

1,329 / —

Human votes vs benchmarks, Elo-eq

Value

-36

$0.4378 per 1M tokens, median of 3 providers

On your hardware

Does not fit the reference setups.

Score decomposition

C General 1,321 [1,319–1,324] Percentile 39 · #179 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,343 ±2.18 1,343 ±2 26.0% 2026-10-02 —
LMArena text/hard_prompts 1,339 ±2.80 1,340 ±2 25.8% 2026-10-02 —
LMArena text/instruction_following 1,312 ±3.43 1,330 ±3 12.7% 2026-10-02 —
LMArena text/expert 1,315 ±7.48 1,325 ±6 11.4% 2026-10-02 —
LMArena text/longer_query 1,326 ±3.75 1,332 ±4 6.3% 2026-10-02 —
LMArena text/multi_turn 1,335 ±4.19 1,340 ±4 6.2% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Coding 1,330 [1,324–1,336] Percentile 36 · #177 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,358 ±3.90 1,344 ±4 90.1% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Math 1,335 [1,324–1,347] Percentile 41 · #151 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,360 ±6.94 1,355 ±7 87.0% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Writing 1,319 [1,313–1,325] Percentile 42 · #156 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,298 ±4.63 1,324 ±5 61.6% 2026-10-02 —
LMArena text/longer_query 1,326 ±3.75 1,332 ±4 32.1% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: 繁體中文 1,334 [1,324–1,343] Percentile 35 · #146 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,361 ±6.32 1,343 ±5 93.5% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: Deutsch 1,346 [1,330–1,363] Percentile 32 · #99 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,350 ±10 1,359 ±9 92.2% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: English 1,340 [1,334–1,345] Percentile 43 · #155 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,363 ±2.85 1,349 ±3 93.9% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: Español 1,344 [1,326–1,362] Percentile 18 · #122 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,355 ±11 1,357 ±10 91.8% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: Français 1,343 [1,320–1,366] Percentile 21 · #107 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,369 ±14 1,358 ±13 90.3% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: 日本語 1,285 [1,270–1,300] Percentile 19 · #104 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,219 ±11 1,292 ±8 92.4% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: 한국어 1,321 [1,304–1,338] Percentile 22 · #106 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,263 ±12 1,331 ±9 92.0% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: Polski 1,338 [1,329–1,346] Percentile 15 · #112 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,329 ±5.46 1,347 ±5 93.6% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: Русский 1,334 [1,325–1,344] Percentile 36 · #150 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,330 ±5.91 1,344 ±5 93.4% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

History

fedi-index by month
The same in a table
Model 2026-10
MiniMax M1 1,321 C

Badge

Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.

fedi-index: MiniMax M1

Data CC BY 4.0: keep the link to fedi.software.