Muse Wonder in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
S 1,490 ±8
Percentile 98 · #7
People prefer / Solves tasks
1,480 / 1,503
Human votes vs benchmarks, Elo-eq
Value
+52
$8 per 1M tokens, median of 3 providers
On your hardware
Closed weights: cloud only.
Score decomposition
S General 1,490 [1,482–1,498] Percentile 98 · #7 · components: 7
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
162 ±1.27 | 1,530 ±10 | 39.9% | 2026-10-12 | — |
| LMArena |
text/overall
|
1,503 ±3.15 | 1,503 ±3 | 15.8% | 2026-11-11 | max |
| LMArena |
text/hard_prompts
|
1,514 ±3.84 | 1,498 ±4 | 15.6% | 2026-11-11 | max |
| LMArena |
text/instruction_following
|
1,494 ±4.93 | 1,502 ±5 | 7.5% | 2026-11-11 | max |
| LMArena |
text/expert
|
1,514 ±8.65 | 1,488 ±7 | 6.7% | 2026-11-11 | max |
| LMArena |
text/longer_query
|
1,497 ±4.53 | 1,491 ±4 | 3.8% | 2026-11-11 | max |
| LMArena |
text/multi_turn
|
1,514 ±7.46 | 1,502 ±7 | 3.4% | 2026-11-11 | max |
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 1,463 [1,459–1,467] Percentile 95 · #16 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,647 ±4.67 | 1,492 ±1 | 35.2% | 2026-11-15 | max |
| LMArena |
text/coding
|
1,516 ±5.77 | 1,484 ±5 | 31.8% | 2026-11-11 | max |
| Terminal-Bench |
tbench/terminal-bench
decay ×0.90 |
0.47 ±0.02 | 1,488 ±4 | 24.1% | 2026-10-12 | 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
B Agents 1,444 [1,440–1,449] Percentile 77 · #19 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.01 ±0.01 | 1,460 ±3 | 67.4% | 2026-11-15 | max |
| Terminal-Bench |
tbench/terminal-bench
decay ×0.90 |
0.47 ±0.02 | 1,488 ±4 | 23.8% | 2026-10-12 | 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 1,426 [1,407–1,444] Percentile 81 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,478 ±11 | 1,468 ±11 | 83.9% | 2026-11-11 | max |
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 1,491 [1,483–1,499] Percentile 96 · #11 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,493 ±6.19 | 1,523 ±6 | 60.4% | 2026-11-11 | max |
| LMArena |
text/longer_query
|
1,497 ±4.53 | 1,491 ±4 | 33.0% | 2026-11-11 | max |
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 1,461 [1,448–1,475] Percentile 93 · #16 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,536 ±9.59 | 1,482 ±8 | 92.7% | 2026-11-11 | max |
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 1,484 [1,475–1,493] Percentile 98 · #5 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,509 ±4.75 | 1,503 ±5 | 93.5% | 2026-11-11 | max |
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 1,444 [1,421–1,466] Percentile 85 · #24 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,477 ±14 | 1,470 ±13 | 90.2% | 2026-11-11 | max |
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 1,461 [1,438–1,484] Percentile 94 · #9 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,512 ±14 | 1,489 ±13 | 90.2% | 2026-11-11 | max |
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 1,488 [1,476–1,500] Percentile 97 · #7 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,514 ±7.30 | 1,509 ±7 | 93.1% | 2026-11-11 | max |
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 | 2026-11 |
|---|---|
| Muse Wonder | 1,490 S |
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.