ernie-5.0-0110 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,406 ±2
Percentile 72 · #83 · provisional
People prefer / Solves tasks
1,419 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,406 [1,404–1,408] Percentile 72 · #83 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,445 ±1.97 | 1,445 ±2 | 25.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,445 ±2.42 | 1,436 ±2 | 25.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,413 ±3.08 | 1,425 ±3 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,427 ±5.54 | 1,416 ±4 | 12.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,422 ±3.06 | 1,421 ±3 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,433 ±4.04 | 1,429 ±4 | 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
B Coding 1,408 [1,403–1,413] Percentile 72 · #79 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,455 ±3.35 | 1,430 ±3 | 90.2% | 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 Math 1,400 [1,389–1,410] Percentile 71 · #75 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,437 ±6.29 | 1,428 ±6 | 87.3% | 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 Vision 1,409 [1,402–1,416] Percentile 51 · #56 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,248 ±5.66 | 1,428 ±5 | 65.3% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,249 ±7.14 | 1,422 ±7 | 15.0% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,236 ±11 | 1,406 ±10 | 12.9% | 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 Writing 1,429 [1,423–1,434] Percentile 78 · #59 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,426 ±4.15 | 1,455 ±4 | 61.6% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,422 ±3.06 | 1,421 ±3 | 32.1% | 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
A Language: 繁體中文 1,440 [1,418–1,461] Percentile 83 · #38 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,513 ±15 | 1,464 ±12 | 90.6% | 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
B Language: English 1,424 [1,419–1,430] Percentile 76 · #65 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,448 ±2.73 | 1,439 ±3 | 93.9% | 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: 日本語 1,394 [1,373–1,416] Percentile 48 · #67 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,383 ±16 | 1,414 ±12 | 90.7% | 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
B Language: 한국어 1,421 [1,405–1,438] Percentile 71 · #40 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,406 ±12 | 1,440 ±9 | 92.1% | 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
A Language: Русский 1,433 [1,426–1,440] Percentile 80 · #47 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,446 ±4.45 | 1,448 ±4 | 93.7% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| ernie-5.0-0110 | 1,406 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.