alpaca-13b in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 966 ±6
Percentile 1 · #290 · provisional
People prefer / Solves tasks
945 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 966 [960–972] Percentile 1 · #290 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
933 ±5.75 | 933 ±6 | 40.9% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
891 ±8.24 | 931 ±8 | 18.4% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
outlier |
826 ±9.78 | 876 ±9 | 17.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
884 ±13 | 931 ±12 | 7.2% | 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
D Coding 898 [878–918] Percentile 1 · #276 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
799 ±14 | 845 ±12 | 85.3% | 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
D Math 967 [949–985] Percentile 1 · #252 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
908 ±12 | 921 ±11 | 83.8% | 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
D Writing 1,006 [986–1,027] Percentile 2 · #262 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
968 ±11 | 987 ±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: English 940 [928–952] Percentile 2 · #269 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
957 ±6.27 | 920 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| alpaca-13b | 966 D |
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.