Skip to content
fedi.software

Mistral Medium 3.1 in fedi-index

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

fedi-index · General

B 1,392 ±1

Percentile 62 · #112 · provisional

People prefer / Solves tasks

1,403 / —

Human votes vs benchmarks, Elo-eq

Value

+24

$0.80 per 1M tokens, median of 3 providers

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,392 [1,390–1,393] Percentile 62 · #112 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,425 ±1.31 1,425 ±1 25.6% 2026-11-11 —
LMArena text/hard_prompts 1,426 ±1.68 1,418 ±2 25.5% 2026-11-11 —
LMArena text/instruction_following 1,398 ±2.10 1,411 ±2 12.7% 2026-11-11 —
LMArena text/expert 1,409 ±3.83 1,402 ±3 12.4% 2026-11-11 —
LMArena text/longer_query 1,406 ±2.14 1,406 ±2 6.3% 2026-11-11 —
LMArena text/multi_turn 1,419 ±2.60 1,416 ±2 6.3% 2026-11-11 —

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 Coding 1,388 [1,384–1,391] Percentile 58 · #120 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,434 ±2.32 1,411 ±2 88.7% 2026-11-11 —

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 Math 1,378 [1,372–1,385] Percentile 53 · #121 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,409 ±3.94 1,402 ±4 88.3% 2026-11-11 —

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 Vision 1,347 [1,343–1,351] Percentile 24 · #84 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,172 ±3.14 1,360 ±3 63.4% 2026-11-09 —
LMArena vision/ocr 1,175 ±3.74 1,350 ±4 15.5% 2026-11-09 —
LMArena vision/diagram 1,174 ±5.42 1,352 ±5 14.9% 2026-11-09 —

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 Writing 1,402 [1,398–1,406] Percentile 64 · #96 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,391 ±2.79 1,419 ±3 62.3% 2026-11-11 —
LMArena text/longer_query 1,406 ±2.14 1,406 ±2 31.7% 2026-11-11 —

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: 繁體中文 1,399 [1,393–1,404] Percentile 55 · #100 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,447 ±3.72 1,411 ±3 93.9% 2026-11-11 —

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: Deutsch 1,416 [1,404–1,427] Percentile 63 · #54 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,434 ±7.45 1,431 ±6 93.1% 2026-11-11 —

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: English 1,415 [1,411–1,418] Percentile 68 · #86 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,438 ±1.82 1,428 ±2 94.0% 2026-11-11 —

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: Español 1,415 [1,405–1,425] Percentile 56 · #66 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,434 ±6.05 1,430 ±6 93.4% 2026-11-11 —

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: Français 1,425 [1,413–1,437] Percentile 64 · #51 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,460 ±7.09 1,442 ±6 93.1% 2026-11-11 —

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: 日本語 1,397 [1,385–1,410] Percentile 49 · #65 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,380 ±9.17 1,412 ±7 93.0% 2026-11-11 —

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: 한국어 1,406 [1,396–1,416] Percentile 57 · #60 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,381 ±7.16 1,420 ±5 93.4% 2026-11-11 —

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: Polski 1,418 [1,410–1,426] Percentile 59 · #54 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,430 ±5.37 1,432 ±4 93.6% 2026-11-11 —

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: Русский 1,404 [1,399–1,410] Percentile 62 · #89 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,412 ±3.17 1,417 ±3 93.9% 2026-11-11 —

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 2026-11
Mistral Medium 3.1 1,392 B

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: Mistral Medium 3.1

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