Skip to content
fedi.software

Hunyuan Standard (2025-02-10) in fedi-index

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

fedi-index · General

C 1,265 ±6

Percentile 30 · #207 · provisional

People prefer / Solves tasks

1,270 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,265 [1,259–1,271] Percentile 30 · #207 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,274 ±4.92 1,274 ±5 32.9% 2026-11-11 2025-02-10
LMArena text/hard_prompts 1,264 ±9.47 1,272 ±9 27.5% 2026-11-11 2025-02-10
LMArena text/instruction_following 1,245 ±7.72 1,266 ±7 14.7% 2026-11-11 2025-02-10
LMArena text/multi_turn 1,275 ±12 1,285 ±11 5.9% 2026-11-11 2025-02-10
LMArena text/longer_query 1,301 ±14 1,308 ±13 5.3% 2026-11-11 2025-02-10

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 Coding 1,255 [1,238–1,273] Percentile 27 · #209 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,270 ±12 1,265 ±11 84.1% 2026-11-11 2025-02-10

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 Math 1,261 [1,242–1,280] Percentile 31 · #177 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,274 ±12 1,272 ±12 83.3% 2026-11-11 2025-02-10

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 Writing 1,273 [1,257–1,289] Percentile 34 · #174 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,242 ±12 1,267 ±12 61.0% 2026-11-11 2025-02-10
LMArena text/longer_query 1,301 ±14 1,308 ±13 29.5% 2026-11-11 2025-02-10

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: 繁體中文 1,300 [1,277–1,322] Percentile 30 · #153 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,319 ±16 1,310 ±12 90.4% 2026-11-11 2025-02-10

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: English 1,259 [1,246–1,271] Percentile 32 · #184 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,281 ±6.32 1,263 ±7 93.0% 2026-11-11 2025-02-10

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

D Language: Русский 1,272 [1,250–1,294] Percentile 24 · #174 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,258 ±14 1,279 ±12 90.5% 2026-11-11 2025-02-10

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
Hunyuan Standard (2025-02-10) 1,265 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: Hunyuan Standard (2025-02-10)

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