Skip to content
fedi.software

Hunyuan T1 (20250711) in fedi-index

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

fedi-index · General

B 1,370 ±5

Percentile 50 · #149 · provisional

People prefer / Solves tasks

1,382 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,370 [1,365–1,376] Percentile 50 · #149 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,401 ±4.42 1,401 ±4 31.9% 2026-11-11 20250711
LMArena text/hard_prompts 1,399 ±6.67 1,394 ±6 29.8% 2026-11-11 20250711
LMArena text/instruction_following 1,375 ±8.90 1,390 ±8 13.2% 2026-11-11 20250711
LMArena text/longer_query 1,385 ±9.82 1,386 ±9 6.3% 2026-11-11 20250711
LMArena text/multi_turn 1,393 ±11 1,393 ±10 5.9% 2026-11-11 20250711

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 1,347 [1,332–1,362] Percentile 42 · #167 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,390 ±10 1,372 ±9 85.5% 2026-11-11 20250711

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 1,390 [1,374–1,405] Percentile 59 · #109 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,392 ±12 1,421 ±12 56.5% 2026-11-11 20250711
LMArena text/longer_query 1,385 ±9.82 1,386 ±9 34.6% 2026-11-11 20250711

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 1,376 [1,353–1,398] Percentile 43 · #126 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,426 ±16 1,394 ±13 90.3% 2026-11-11 20250711

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: English 1,372 [1,359–1,385] Percentile 52 · #130 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,397 ±6.78 1,385 ±7 92.9% 2026-11-11 20250711

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 1,376 [1,354–1,399] Percentile 26 · #97 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,386 ±15 1,395 ±13 90.2% 2026-11-11 20250711

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 1,372 [1,347–1,397] Percentile 45 · #127 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,384 ±16 1,392 ±14 89.4% 2026-11-11 20250711

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 T1 (20250711) 1,370 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: Hunyuan T1 (20250711)

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