palm-2 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,056 ±6
Percentile 5 · #278 · provisional
People prefer / Solves tasks
1,046 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,056 [1,050–1,062] Percentile 5 · #278 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,027 ±4.70 | 1,027 ±5 | 34.0% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,005 ±7.85 | 1,038 ±7 | 30.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,010 ±6.80 | 1,044 ±6 | 15.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
994 ±9.97 | 1,031 ±9 | 6.9% | 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
D Coding 1,043 [1,027–1,059] Percentile 3 · #269 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
994 ±11 | 1,020 ±9 | 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
D Math 1,078 [1,062–1,094] Percentile 7 · #237 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,049 ±9.88 | 1,056 ±10 | 85.1% | 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 Writing 1,026 [1,010–1,042] Percentile 4 · #257 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
991 ±8.83 | 1,011 ±9 | 92.2% | 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 Language: 繁體中文 993 [967–1,019] Percentile 1 · #221 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
887 ±19 | 966 ±15 | 88.9% | 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
D Language: English 1,044 [1,034–1,054] Percentile 5 · #259 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,063 ±5.08 | 1,032 ±5 | 93.4% | 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 |
|---|---|
| palm-2 | 1,056 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.