Skip to content
fedi.software

Mistral Large 2 (2407) in fedi-index

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

fedi-index · General

C 1,258 ±2

Percentile 29 · #211 · provisional

People prefer / Solves tasks

1,262 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,258 [1,256–1,260] Percentile 29 · #211 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,266 ±1.99 1,266 ±2 26.0% 2026-11-11 2407
LMArena text/hard_prompts 1,256 ±3.21 1,265 ±3 25.5% 2026-11-11 2407
LMArena text/instruction_following 1,248 ±2.88 1,269 ±3 12.8% 2026-11-11 2407
LMArena text/expert 1,232 ±6.39 1,257 ±5 11.8% 2026-11-11 2407
LMArena text/multi_turn 1,257 ±4.04 1,269 ±4 6.2% 2026-11-11 2407
LMArena text/longer_query 1,257 ±4.39 1,267 ±4 6.2% 2026-11-11 2407

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 1,263 [1,257–1,269] Percentile 29 · #205 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,277 ±3.98 1,271 ±4 88.3% 2026-11-11 2407

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 1,254 [1,247–1,260] Percentile 29 · #181 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,262 ±4.15 1,260 ±4 88.2% 2026-11-11 2407

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 1,263 [1,257–1,269] Percentile 32 · #180 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,243 ±4.35 1,268 ±4 62.2% 2026-11-11 2407
LMArena text/longer_query 1,257 ±4.39 1,267 ±4 31.5% 2026-11-11 2407

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: 繁體中文 1,244 [1,236–1,252] Percentile 23 · #169 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,240 ±5.44 1,247 ±4 93.7% 2026-11-11 2407

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: Deutsch 1,271 [1,256–1,285] Percentile 19 · #117 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,254 ±9.11 1,276 ±8 92.6% 2026-11-11 2407

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 1,267 [1,262–1,272] Percentile 34 · #179 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,289 ±2.60 1,271 ±3 93.9% 2026-11-11 2407

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 1,243 [1,221–1,265] Percentile 7 · #139 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,236 ±13 1,247 ±12 90.6% 2026-11-11 2407

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 1,263 [1,239–1,288] Percentile 10 · #128 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,273 ±15 1,270 ±14 89.6% 2026-11-11 2407

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 1,264 [1,251–1,276] Percentile 13 · #111 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,188 ±9.22 1,268 ±7 93.0% 2026-11-11 2407

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 1,256 [1,239–1,273] Percentile 11 · #122 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,170 ±12 1,261 ±9 92.0% 2026-11-11 2407

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 1,273 [1,266–1,281] Percentile 25 · #172 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,257 ±4.47 1,278 ±4 93.7% 2026-11-11 2407

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 Large 2 (2407) 1,258 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 Large 2 (2407)

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