hunyuan-vision-1.5-thinking in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,380 ±7
Percentile 57 · #126 · provisional
People prefer / Solves tasks
1,393 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,380 [1,373–1,387] Percentile 57 · #126 · components: 5 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,406 ±6.34 | 1,406 ±6 | 32.2% | 2026-10-02 | thinking |
| LMArena |
text/hard_prompts
|
1,417 ±8.80 | 1,410 ±8 | 29.7% | 2026-10-02 | thinking |
| LMArena |
text/instruction_following
|
1,398 ±11 | 1,411 ±11 | 12.6% | 2026-10-02 | thinking |
| LMArena |
text/longer_query
|
1,405 ±13 | 1,405 ±12 | 5.9% | 2026-10-02 | thinking |
| LMArena |
text/multi_turn
|
1,424 ±14 | 1,420 ±13 | 5.4% | 2026-10-02 | thinking |
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 1,369 [1,348–1,390] Percentile 52 · #133 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,419 ±14 | 1,399 ±12 | 85.0% | 2026-10-02 | thinking |
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 1,353 [1,345–1,361] Percentile 30 · #80 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,180 ±6.19 | 1,367 ±6 | 66.4% | 2026-10-02 | thinking |
| LMArena |
vision/ocr
|
1,176 ±8.03 | 1,352 ±8 | 14.9% | 2026-10-02 | thinking |
| LMArena |
vision/diagram
|
1,196 ±13 | 1,370 ±12 | 11.5% | 2026-10-02 | thinking |
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 1,387 [1,366–1,408] Percentile 59 · #110 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/longer_query
|
1,405 ±13 | 1,405 ±12 | 90.8% | 2026-10-02 | thinking |
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 1,399 [1,382–1,417] Percentile 63 · #102 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,428 ±9.40 | 1,417 ±10 | 91.8% | 2026-10-02 | thinking |
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-vision-1.5-thinking | 1,380 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.