Skip to content
fedi.software

Mistral Small 3.2 (2506) in fedi-index

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

fedi-index · General

C 1,317 ±3

Percentile 37 · #187 · provisional

People prefer / Solves tasks

1,324 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,317 [1,314–1,320] Percentile 37 · #187 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,338 ±2.65 1,338 ±3 26.5% 2026-11-11 —
LMArena text/hard_prompts 1,335 ±3.52 1,336 ±3 26.1% 2026-11-11 —
LMArena text/instruction_following 1,309 ±4.52 1,327 ±4 12.6% 2026-11-11 —
LMArena text/expert 1,291 ±9.92 1,306 ±8 10.6% 2026-11-11 —
LMArena text/longer_query 1,326 ±5.10 1,331 ±5 6.2% 2026-11-11 —
LMArena text/multi_turn 1,343 ±5.46 1,348 ±5 6.2% 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 Coding 1,330 [1,322–1,338] Percentile 36 · #183 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,363 ±5.14 1,348 ±5 88.0% 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

C Math 1,318 [1,304–1,333] Percentile 38 · #160 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,342 ±8.88 1,338 ±8 85.8% 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 1,317 [1,311–1,323] Percentile 19 · #90 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,142 ±4.62 1,332 ±4 64.7% 2026-11-09 —
LMArena vision/ocr 1,134 ±5.72 1,311 ±6 15.3% 2026-11-09 —
LMArena vision/diagram 1,125 ±9.15 1,308 ±8 13.5% 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

C Writing 1,322 [1,314–1,331] Percentile 43 · #151 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,304 ±6.49 1,331 ±7 60.4% 2026-11-11 —
LMArena text/longer_query 1,326 ±5.10 1,331 ±5 32.8% 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: 繁體中文 1,318 [1,305–1,330] Percentile 32 · #150 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,340 ±8.90 1,326 ±7 92.9% 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

C Language: Deutsch 1,336 [1,313–1,359] Percentile 29 · #103 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,340 ±15 1,350 ±13 90.2% 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: English 1,335 [1,328–1,342] Percentile 42 · #157 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,358 ±3.56 1,344 ±4 93.8% 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 Language: Español 1,334 [1,310–1,358] Percentile 14 · #129 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,346 ±15 1,349 ±14 89.6% 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

D Language: 日本語 1,323 [1,305–1,341] Percentile 24 · #97 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,275 ±13 1,334 ±10 91.8% 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 Language: 한국어 1,314 [1,292–1,336] Percentile 21 · #109 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,256 ±16 1,326 ±12 90.6% 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

D Language: Polski 1,328 [1,316–1,339] Percentile 8 · #120 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,317 ±7.48 1,337 ±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: Русский 1,328 [1,315–1,342] Percentile 34 · #153 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,324 ±8.17 1,338 ±7 92.8% 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 Small 3.2 (2506) 1,317 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: Mistral Small 3.2 (2506)

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