StableLM Tuned Alpha 7B in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 923 ±8
Percentile 1 · #295 · provisional
People prefer / Solves tasks
901 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 923 [915–931] Percentile 1 · #295 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
867 ±6.40 | 867 ±6 | 36.5% | 2026-11-11 | — |
| LMArena |
text/hard_prompts
|
835 ±12 | 885 ±11 | 28.0% | 2026-11-11 | — |
| LMArena |
text/instruction_following
|
831 ±10 | 874 ±10 | 15.3% | 2026-11-11 | — |
| LMArena |
text/multi_turn
|
821 ±17 | 873 ±15 | 5.2% | 2026-11-11 | — |
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 977 [954–1,000] Percentile 1 · #283 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
886 ±16 | 923 ±14 | 80.6% | 2026-11-11 | — |
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 921 [899–943] Percentile 0 · #256 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
839 ±15 | 855 ±14 | 81.1% | 2026-11-11 | — |
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 918 [893–943] Percentile 1 · #262 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
868 ±14 | 884 ±14 | 89.4% | 2026-11-11 | — |
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 875 [861–888] Percentile 1 · #267 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
890 ±7.08 | 849 ±8 | 92.8% | 2026-11-11 | — |
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 | 2026-11 |
|---|---|---|
| StableLM Tuned Alpha 7B | 916 | 923 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.