Skip to content
fedi.software

hunyuan-turbos-20250416 in fedi-index

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

fedi-index · General

C 1,348 ±4

Percentile 47 · #156 · provisional

People prefer / Solves tasks

1,358 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,348 [1,344–1,352] Percentile 47 · #156 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,377 ±3.30 1,377 ±3 27.2% 2026-10-02 —
LMArena text/hard_prompts 1,373 ±4.85 1,371 ±4 26.2% 2026-10-02 —
LMArena text/instruction_following 1,343 ±6.03 1,360 ±6 12.4% 2026-10-02 —
LMArena text/expert 1,338 ±12 1,344 ±10 9.9% 2026-10-02 —
LMArena text/multi_turn 1,387 ±7.26 1,387 ±7 6.0% 2026-10-02 —
LMArena text/longer_query 1,365 ±7.60 1,367 ±7 5.8% 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 Coding 1,331 [1,320–1,342] Percentile 37 · #176 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,361 ±6.98 1,347 ±6 89.1% 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 Math 1,332 [1,316–1,347] Percentile 40 · #154 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,359 ±9.81 1,354 ±9 85.2% 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

B Writing 1,366 [1,356–1,377] Percentile 52 · #128 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,358 ±7.90 1,386 ±8 60.7% 2026-10-02 —
LMArena text/longer_query 1,365 ±7.60 1,367 ±7 32.0% 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 1,371 [1,353–1,390] Percentile 45 · #124 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,416 ±13 1,387 ±10 91.6% 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: Deutsch 1,347 [1,322–1,372] Percentile 33 · #97 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,356 ±17 1,364 ±14 89.3% 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

B Language: English 1,363 [1,354–1,371] Percentile 52 · #132 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,386 ±4.27 1,374 ±4 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

C Language: 日本語 1,363 [1,340–1,385] Percentile 34 · #85 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,338 ±17 1,380 ±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: Polski 1,374 [1,356–1,392] Percentile 29 · #93 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,379 ±12 1,390 ±10 91.7% 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 1,365 [1,350–1,379] Percentile 45 · #130 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,368 ±8.87 1,378 ±8 92.6% 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
hunyuan-turbos-20250416 1,348 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-turbos-20250416

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