hunyuan-large-vision in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,258 ±5
Percentile 28 · #210 · provisional
People prefer / Solves tasks
1,262 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,258 [1,253–1,264] Percentile 28 · #210 · components: 5 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,263 ±4.73 | 1,263 ±5 | 31.5% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,256 ±6.81 | 1,265 ±6 | 29.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,249 ±8.65 | 1,270 ±8 | 13.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,254 ±10 | 1,266 ±9 | 6.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,279 ±10 | 1,287 ±10 | 6.2% | 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
C Coding 1,287 [1,272–1,302] Percentile 30 · #196 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,307 ±9.73 | 1,299 ±9 | 87.8% | 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 Math 1,254 [1,231–1,278] Percentile 30 · #179 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,268 ±16 | 1,267 ±15 | 80.1% | 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 Vision 1,350 [1,338–1,362] Percentile 29 · #81 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,180 ±8.35 | 1,366 ±8 | 76.0% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,167 ±10 | 1,343 ±10 | 16.5% | 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
C Writing 1,273 [1,257–1,288] Percentile 32 · #182 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,250 ±12 | 1,275 ±13 | 56.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,279 ±10 | 1,287 ±10 | 34.5% | 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
D Language: 繁體中文 1,277 [1,254–1,300] Percentile 25 · #168 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,289 ±17 | 1,286 ±13 | 90.0% | 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: English 1,258 [1,246–1,271] Percentile 30 · #191 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,281 ±6.33 | 1,263 ±7 | 93.0% | 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
D Language: Polski 1,263 [1,243–1,284] Percentile 1 · #130 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,237 ±14 | 1,269 ±12 | 91.0% | 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
D Language: Русский 1,260 [1,237–1,282] Percentile 22 · #183 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,243 ±14 | 1,266 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| hunyuan-large-vision | 1,258 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.