hunyuan-hy3-preview in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,379 ±4
Percentile 57 · #127 · provisional
People prefer / Solves tasks
1,391 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,379 [1,375–1,383] Percentile 57 · #127 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,401 ±3.77 | 1,401 ±4 | 26.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,413 ±4.62 | 1,407 ±4 | 26.4% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,384 ±6.39 | 1,397 ±6 | 12.2% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,422 ±11 | 1,413 ±9 | 10.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,403 ±5.77 | 1,403 ±5 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,411 ±8.97 | 1,408 ±8 | 5.5% | 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 Coding 1,384 [1,379–1,390] Percentile 60 · #113 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,356 ±8.81 | 1,409 ±2 | 47.7% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,422 ±6.84 | 1,401 ±6 | 42.1% | 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
B Math 1,378 [1,357–1,399] Percentile 56 · #113 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,425 ±14 | 1,417 ±13 | 82.0% | 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
B Writing 1,367 [1,356–1,379] Percentile 53 · #126 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,339 ±9.65 | 1,366 ±10 | 56.6% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,403 ±5.77 | 1,403 ±5 | 35.9% | 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 Language: 繁體中文 1,382 [1,362–1,403] Percentile 49 · #115 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,433 ±15 | 1,400 ±12 | 90.9% | 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
B Language: English 1,385 [1,375–1,395] Percentile 58 · #116 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,409 ±5.26 | 1,398 ±6 | 93.4% | 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: Русский 1,387 [1,369–1,406] Percentile 54 · #108 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,397 ±12 | 1,404 ±10 | 91.5% | 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
The same in a table
| Model | 2026-10 |
|---|---|
| hunyuan-hy3-preview | 1,379 B |
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.