Skip to content
fedi.software

amazon-nova-experimental-chat (26-02-10) in fedi-index

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

fedi-index · General

B 1,414 ±5

Percentile 74 · #78 · provisional

People prefer / Solves tasks

1,429 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,414 [1,409–1,419] Percentile 74 · #78 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,449 ±4.92 1,449 ±5 31.4% 2026-11-11 26-02-10
LMArena text/hard_prompts 1,459 ±6.38 1,448 ±6 30.3% 2026-11-11 26-02-10
LMArena text/instruction_following 1,427 ±9.12 1,439 ±9 13.0% 2026-11-11 26-02-10
LMArena text/longer_query 1,442 ±9.07 1,440 ±8 6.6% 2026-11-11 26-02-10
LMArena text/multi_turn 1,442 ±12 1,437 ±11 5.7% 2026-11-11 26-02-10

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 1,419 [1,405–1,434] Percentile 77 · #68 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,483 ±9.79 1,456 ±9 85.7% 2026-11-11 26-02-10

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 1,394 [1,378–1,409] Percentile 61 · #103 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,367 ±13 1,395 ±13 54.1% 2026-11-11 26-02-10
LMArena text/longer_query 1,442 ±9.07 1,440 ±8 36.8% 2026-11-11 26-02-10

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 1,404 [1,381–1,426] Percentile 56 · #96 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,465 ±16 1,425 ±13 90.2% 2026-11-11 26-02-10

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 1,380 [1,360–1,401] Percentile 44 · #81 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,395 ±14 1,398 ±12 90.9% 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

A Language: English 1,432 [1,416–1,447] Percentile 82 · #48 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,459 ±7.98 1,450 ±8 92.4% 2026-11-11 26-02-10

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 1,419 [1,401–1,437] Percentile 60 · #60 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,443 ±11 1,439 ±10 91.7% 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: Français 1,412 [1,391–1,432] Percentile 52 · #68 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,449 ±12 1,432 ±11 91.1% 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: 한국어 1,403 [1,382–1,424] Percentile 54 · #64 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,384 ±15 1,423 ±12 90.9% 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: Polski 1,390 [1,374–1,408] Percentile 34 · #87 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,400 ±11 1,407 ±9 92.0% 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: Русский 1,407 [1,387–1,427] Percentile 63 · #86 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,422 ±12 1,427 ±11 91.1% 2026-11-11 26-02-10

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
amazon-nova-experimental-chat (26-02-10) 1,414 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: amazon-nova-experimental-chat (26-02-10)

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