muse-spark in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,439 ±8
Percentile 87 · #40
People prefer / Solves tasks
1,445 / 1,430
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,439 [1,432–1,447] Percentile 87 · #40 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
152 ±1.37 | 1,454 ±11 | 34.4% | 2026-04-08 | — |
| LMArena |
text/overall
|
1,474 ±2.92 | 1,474 ±3 | 16.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,475 ±3.49 | 1,462 ±3 | 16.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,443 ±4.58 | 1,454 ±4 | 8.0% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,458 ±8.16 | 1,442 ±7 | 7.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,452 ±4.35 | 1,448 ±4 | 4.0% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,478 ±6.68 | 1,469 ±6 | 3.7% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.90 ±0.02 | 1,457 ±10 | 1.6% | 2026-04-08 | — |
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 Coding 1,429 [1,421–1,437] Percentile 82 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,482 ±5.03 | 1,455 ±4 | 89.8% | 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
B Math 1,410 [1,394–1,426] Percentile 77 · #59 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,455 ±9.95 | 1,446 ±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
A Vision 1,460 [1,454–1,466] Percentile 90 · #12 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,305 ±4.64 | 1,480 ±4 | 63.8% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,306 ±5.06 | 1,478 ±5 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,309 ±7.74 | 1,471 ±7 | 14.2% | 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
A Writing 1,456 [1,448–1,465] Percentile 90 · #27 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,460 ±6.95 | 1,490 ±7 | 59.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,452 ±4.35 | 1,448 ±4 | 33.8% | 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
A Language: 繁體中文 1,441 [1,426–1,455] Percentile 84 · #37 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,508 ±10 | 1,460 ±8 | 92.5% | 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
A Language: English 1,456 [1,448–1,464] Percentile 93 · #19 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,480 ±3.90 | 1,473 ±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
A Language: Español 1,439 [1,417–1,461] Percentile 82 · #27 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,471 ±13 | 1,464 ±12 | 90.5% | 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
A Language: Français 1,448 [1,425–1,471] Percentile 87 · #19 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,497 ±14 | 1,475 ±13 | 90.1% | 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: Polski 1,441 [1,416–1,466] Percentile 85 · #21 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,473 ±17 | 1,470 ±14 | 89.4% | 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
A Language: Русский 1,449 [1,436–1,461] Percentile 88 · #30 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,467 ±7.72 | 1,467 ±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 |
|---|---|
| muse-spark | 1,439 A |
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.