Muse Spark 1.2 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,457 ±7
Percentile 92 · #23
People prefer / Solves tasks
1,459 / 1,455
Human votes vs benchmarks, Elo-eq
Value
+62
$2 per 1M tokens, median of 13 providers · vendor $0.125
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,457 [1,450–1,464] Percentile 92 · #23 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
155 ±1.17 | 1,476 ±9 | 37.5% | 2026-08-05 | — |
| LMArena |
text/overall
|
1,483 ±4.65 | 1,483 ±5 | 15.7% | 2026-10-02 | xhigh |
| LMArena |
text/hard_prompts
|
1,489 ±5.71 | 1,475 ±5 | 15.4% | 2026-10-02 | xhigh |
| LMArena |
text/instruction_following
|
1,467 ±7.56 | 1,476 ±7 | 7.0% | 2026-10-02 | xhigh |
| LMArena |
text/expert
|
1,485 ±13 | 1,464 ±11 | 5.6% | 2026-10-02 | xhigh |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.60 ±0.02 | 1,487 ±5 | 4.7% | 2026-08-27 | xhigh |
| LMArena |
text/longer_query
|
1,478 ±6.87 | 1,474 ±6 | 3.6% | 2026-10-02 | xhigh |
| LMArena |
text/multi_turn
|
1,509 ±12 | 1,497 ±11 | 2.9% | 2026-10-02 | 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 Coding 1,434 [1,428–1,441] Percentile 86 · #41 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,532 ±6.93 | 1,459 ±2 | 49.6% | 2026-10-01 | xhigh |
| LMArena |
text/coding
|
1,494 ±8.71 | 1,465 ±8 | 39.8% | 2026-10-02 | 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
C Agents 1,417 [1,414–1,420] Percentile 35 · #38 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.03 ±0.00 | 1,440 ±2 | 90.5% | 2026-10-02 | 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 Vision 1,459 [1,450–1,469] Percentile 88 · #15 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,305 ±7.27 | 1,479 ±7 | 65.6% | 2026-10-02 | xhigh |
| LMArena |
vision/ocr
|
1,313 ±8.56 | 1,484 ±8 | 15.0% | 2026-10-02 | xhigh |
| LMArena |
vision/diagram
|
1,317 ±13 | 1,478 ±12 | 12.1% | 2026-10-02 | 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 Writing 1,455 [1,443–1,468] Percentile 89 · #30 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,450 ±11 | 1,480 ±11 | 56.0% | 2026-10-02 | xhigh |
| LMArena |
text/longer_query
|
1,478 ±6.87 | 1,474 ±6 | 36.0% | 2026-10-02 | 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 Language: 繁體中文 1,445 [1,423–1,467] Percentile 87 · #30 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,522 ±16 | 1,471 ±12 | 90.5% | 2026-10-02 | 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 Language: English 1,462 [1,448–1,475] Percentile 96 · #12 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,489 ±6.97 | 1,482 ±7 | 92.8% | 2026-10-02 | 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 Language: Русский 1,456 [1,435–1,477] Percentile 91 · #21 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,483 ±13 | 1,482 ±12 | 90.8% | 2026-10-02 | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Muse Spark 1.2 | 1,457 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.