Muse Spark 1.1 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,452 ±7
Percentile 91 · #28
People prefer / Solves tasks
1,455 / 1,449
Human votes vs benchmarks, Elo-eq
Value
+58
$2 per 1M tokens, median of 12 providers · vendor $2
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,452 [1,446–1,459] Percentile 91 · #28 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
154 ±1.24 | 1,471 ±10 | 34.0% | 2026-07-09 | — |
| LMArena |
text/overall
|
1,479 ±2.23 | 1,479 ±2 | 15.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,486 ±2.58 | 1,472 ±2 | 15.8% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,457 ±3.13 | 1,467 ±3 | 7.8% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,479 ±4.81 | 1,459 ±4 | 7.6% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.58 ±0.02 | 1,479 ±5 | 4.4% | 2026-08-31 | — |
| LMArena |
text/longer_query
|
1,463 ±2.94 | 1,459 ±3 | 3.9% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,484 ±4.33 | 1,475 ±4 | 3.8% | 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 Coding 1,440 [1,437–1,442] Percentile 90 · #29 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,542 ±3.87 | 1,462 ±1 | 46.0% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,497 ±3.39 | 1,468 ±3 | 44.4% | 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
C Agents 1,429 [1,424–1,433] Percentile 47 · #31 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.05 ±0.00 | 1,432 ±1 | 66.9% | 2026-10-02 | — |
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.40 ±0.05 | 1,481 ±8 | 26.1% | 2026-07-23 | xhigh |
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 Math 1,434 [1,422–1,447] Percentile 87 · #34 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,480 ±7.48 | 1,470 ±7 | 86.7% | 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 Vision 1,454 [1,449–1,458] Percentile 83 · #20 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,294 ±3.67 | 1,469 ±3 | 63.3% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,303 ±3.91 | 1,474 ±4 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,308 ±5.83 | 1,470 ±5 | 14.8% | 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 Writing 1,449 [1,444–1,454] Percentile 85 · #40 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,439 ±3.93 | 1,468 ±4 | 61.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,463 ±2.94 | 1,459 ±3 | 32.0% | 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
A Language: 繁體中文 1,450 [1,442–1,459] Percentile 89 · #26 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,518 ±5.94 | 1,467 ±5 | 93.6% | 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
A Language: Deutsch 1,437 [1,418–1,455] Percentile 84 · #24 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,465 ±12 | 1,458 ±10 | 91.6% | 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
A Language: English 1,455 [1,449–1,461] Percentile 93 · #20 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,479 ±2.95 | 1,471 ±3 | 93.9% | 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
A Language: Español 1,440 [1,424–1,455] Percentile 83 · #26 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,466 ±9.36 | 1,459 ±9 | 92.3% | 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
A Language: Français 1,454 [1,439–1,470] Percentile 92 · #11 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,497 ±9.38 | 1,475 ±9 | 92.3% | 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
A Language: 日本語 1,443 [1,426–1,461] Percentile 85 · #20 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,451 ±13 | 1,465 ±10 | 91.9% | 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
A Language: 한국어 1,460 [1,444–1,476] Percentile 93 · #10 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,461 ±12 | 1,481 ±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
A Language: Polski 1,465 [1,446–1,485] Percentile 94 · #9 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,498 ±13 | 1,490 ±11 | 91.4% | 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 1,464 [1,456–1,472] Percentile 94 · #15 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,483 ±4.86 | 1,481 ±4 | 93.6% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Muse Spark 1.1 | 1,452 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.