Skip to content
fedi.software

MiMo-V2.5-Pro in fedi-index

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

fedi-index · General

A 1,443 ±2

Percentile 88 · #36 · provisional

People prefer / Solves tasks

1,457 / —

Human votes vs benchmarks, Elo-eq

Value

+80

$0.5438 per 1M tokens, median of 17 providers · vendor $0.5438

On your hardware

Does not fit the reference setups.

Score decomposition

A General 1,443 [1,441–1,444] Percentile 88 · #36 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,465 ±1.84 1,465 ±2 25.6% 2026-10-02 —
LMArena text/hard_prompts 1,487 ±2.17 1,474 ±2 25.5% 2026-10-02 —
LMArena text/instruction_following 1,477 ±2.64 1,486 ±2 12.6% 2026-10-02 —
LMArena text/expert 1,502 ±4.02 1,478 ±3 12.4% 2026-10-02 —
LMArena text/longer_query 1,482 ±2.51 1,477 ±2 6.3% 2026-10-02 —
LMArena text/multi_turn 1,476 ±3.31 1,468 ±3 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

A Coding 1,433 [1,431–1,436] Percentile 84 · #45 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,478 ±2.75 1,443 ±1 45.8% 2026-10-01 —
LMArena text/coding 1,502 ±2.85 1,472 ±2 44.6% 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

D Agents 1,399 [1,395–1,403] Percentile 16 · #49 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena agent/overall -0.08 ±0.00 1,420 ±2 90.4% 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

A Math 1,438 [1,430–1,448] Percentile 89 · #30 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,482 ±5.42 1,472 ±5 87.7% 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

A Writing 1,455 [1,450–1,459] Percentile 88 · #32 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,439 ±3.26 1,468 ±3 62.1% 2026-10-02 —
LMArena text/longer_query 1,482 ±2.51 1,477 ±2 31.8% 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

A Language: 繁體中文 1,443 [1,436–1,450] Percentile 85 · #35 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,507 ±4.83 1,459 ±4 93.8% 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

A Language: Deutsch 1,432 [1,418–1,447] Percentile 81 · #28 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,456 ±9.34 1,451 ±8 92.6% 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

A Language: English 1,454 [1,449–1,458] Percentile 92 · #23 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,478 ±2.41 1,470 ±2 94.0% 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

A Language: Español 1,449 [1,437–1,461] Percentile 92 · #13 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,474 ±7.21 1,467 ±7 93.0% 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

A Language: Français 1,451 [1,440–1,463] Percentile 90 · #14 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,491 ±6.95 1,470 ±6 93.1% 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

B Language: 日本語 1,421 [1,406–1,435] Percentile 72 · #37 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,415 ±11 1,438 ±8 92.5% 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

A Language: 한국어 1,443 [1,431–1,456] Percentile 87 · #18 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,435 ±9.16 1,462 ±7 92.9% 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

A Language: Polski 1,445 [1,432–1,459] Percentile 88 · #17 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,467 ±8.58 1,464 ±7 92.8% 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

A Language: Русский 1,437 [1,431–1,444] Percentile 83 · #40 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,451 ±3.70 1,453 ±3 93.8% 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

History

fedi-index by month
The same in a table
Model 2026-10
MiMo-V2.5-Pro 1,443 A

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: MiMo-V2.5-Pro

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