Skip to content
fedi.software

athene-v2-chat in fedi-index

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

fedi-index · General

C 1,283 ±3

Percentile 32 · #201 · provisional

People prefer / Solves tasks

1,288 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,283 [1,280–1,285] Percentile 32 · #201 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,291 ±2.32 1,291 ±2 26.2% 2026-10-02 —
LMArena text/hard_prompts 1,293 ±3.74 1,298 ±3 25.5% 2026-10-02 —
LMArena text/instruction_following 1,271 ±3.22 1,290 ±3 12.9% 2026-10-02 —
LMArena text/expert 1,268 ±7.64 1,287 ±6 11.4% 2026-10-02 —
LMArena text/multi_turn 1,286 ±4.70 1,295 ±4 6.2% 2026-10-02 —
LMArena text/longer_query 1,290 ±4.90 1,297 ±5 6.1% 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

C Coding 1,293 [1,286–1,300] Percentile 31 · #192 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,312 ±4.62 1,303 ±4 89.9% 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

C Math 1,286 [1,278–1,294] Percentile 33 · #171 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,300 ±4.85 1,297 ±5 87.9% 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

C Writing 1,268 [1,261–1,274] Percentile 31 · #186 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,234 ±4.97 1,259 ±5 61.9% 2026-10-02 —
LMArena text/longer_query 1,290 ±4.90 1,297 ±5 31.6% 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

C Language: 繁體中文 1,290 [1,279–1,300] Percentile 26 · #165 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,302 ±7.10 1,296 ±6 93.3% 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 Language: Deutsch 1,276 [1,258–1,293] Percentile 22 · #113 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,261 ±11 1,282 ±10 91.8% 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

C Language: English 1,284 [1,279–1,290] Percentile 33 · #183 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,307 ±2.91 1,290 ±3 93.9% 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

D Language: 日本語 1,282 [1,266–1,298] Percentile 18 · #105 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,215 ±12 1,289 ±9 92.2% 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

D Language: 한국어 1,279 [1,256–1,302] Percentile 16 · #115 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,205 ±17 1,287 ±13 90.3% 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

C Language: Русский 1,294 [1,286–1,303] Percentile 28 · #169 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,282 ±5.09 1,301 ±5 93.6% 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

History

fedi-index by month
The same in a table
Model 2026-10
athene-v2-chat 1,283 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: athene-v2-chat

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