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 1,349 ±4
Percentile 46 · #160 · 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 1,349 [1,345–1,352] Percentile 46 · #160 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,377 ±3.29 | 1,377 ±3 | 27.2% | 2026-11-11 | 20250416 |
| LMArena |
text/hard_prompts
|
1,374 ±4.84 | 1,371 ±4 | 26.2% | 2026-11-11 | 20250416 |
| LMArena |
text/instruction_following
|
1,344 ±6.01 | 1,360 ±6 | 12.4% | 2026-11-11 | 20250416 |
| LMArena |
text/expert
|
1,338 ±12 | 1,344 ±10 | 9.9% | 2026-11-11 | 20250416 |
| LMArena |
text/multi_turn
|
1,387 ±7.25 | 1,387 ±7 | 6.0% | 2026-11-11 | 20250416 |
| LMArena |
text/longer_query
|
1,366 ±7.57 | 1,368 ±7 | 5.8% | 2026-11-11 | 20250416 |
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 1,328 [1,318–1,339] Percentile 36 · #184 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,361 ±6.97 | 1,347 ±6 | 87.2% | 2026-11-11 | 20250416 |
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 1,331 [1,316–1,347] Percentile 39 · #157 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,359 ±9.76 | 1,353 ±9 | 85.2% | 2026-11-11 | 20250416 |
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 1,367 [1,356–1,378] Percentile 51 · #129 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,359 ±7.88 | 1,386 ±8 | 60.7% | 2026-11-11 | 20250416 |
| LMArena |
text/longer_query
|
1,366 ±7.57 | 1,368 ±7 | 32.0% | 2026-11-11 | 20250416 |
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 1,372 [1,354–1,390] Percentile 42 · #128 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,417 ±13 | 1,387 ±10 | 91.7% | 2026-11-11 | 20250416 |
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 1,346 [1,321–1,371] Percentile 31 · #101 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,355 ±17 | 1,363 ±14 | 89.3% | 2026-11-11 | 20250416 |
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 1,363 [1,355–1,371] Percentile 50 · #136 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,386 ±4.27 | 1,374 ±4 | 93.6% | 2026-11-11 | 20250416 |
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 1,366 [1,344–1,388] Percentile 32 · #87 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,342 ±17 | 1,383 ±13 | 90.4% | 2026-11-11 | 20250416 |
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: Polski 1,374 [1,356–1,392] Percentile 24 · #100 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,379 ±12 | 1,390 ±10 | 91.7% | 2026-11-11 | 20250416 |
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 1,364 [1,350–1,379] Percentile 42 · #133 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,367 ±8.85 | 1,377 ±8 | 92.6% | 2026-11-11 | 20250416 |
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
The same in a table
| Model | 2026-11 |
|---|---|
| Hunyuan TurboS (20250416) | 1,349 C |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.