granite-4.2-3b in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,288 ±6
Percentile 32 · #198 · provisional
People prefer / Solves tasks
1,295 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,288 [1,282–1,294] Percentile 32 · #198 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,293 ±5.87 | 1,293 ±6 | 28.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,307 ±7.44 | 1,310 ±7 | 27.1% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,273 ±10 | 1,292 ±10 | 11.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,316 ±18 | 1,325 ±15 | 8.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,291 ±9.30 | 1,298 ±9 | 6.1% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,293 ±15 | 1,302 ±13 | 4.6% | 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
C Coding 1,330 [1,313–1,346] Percentile 36 · #178 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,363 ±11 | 1,348 ±10 | 87.0% | 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 Writing 1,242 [1,223–1,261] Percentile 28 · #192 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,205 ±14 | 1,229 ±15 | 64.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
outlier |
1,291 ±9.30 | 1,298 ±9 | 23.6% | 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
C Language: English 1,295 [1,279–1,312] Percentile 35 · #179 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,320 ±8.69 | 1,303 ±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
D Language: Русский 1,264 [1,237–1,291] Percentile 23 · #180 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,250 ±17 | 1,272 ±16 | 88.5% | 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 |
|---|---|
| granite-4.2-3b | 1,288 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.