Muse Spark 1.1
MetaProprietaryReleased Jul 9, 2026
On the arena.ai Agents leaderboard, Muse Spark 1.1 has a task success rate of -6.60% (—, rank #40, 95% interval -7.25%–-5.95%). Muse Spark 1.1 ranks #14 on the LMArena Text leaderboard (style control) with an Arena score of 1490.4 (±4.2, 44,815 votes). Artificial Analysis Intelligence Index: 33.7. API price: $1.25 input / $4.25 output per 1M tokens. Context: 1.05M. Nearest rivals: Claude Opus 5 (1491.1) above and Muse Spark (1489.0) below.
Quick answer
- Agents leaderboard
- #40 of 45 · -6.60% success
- Text (LMArena)
- #14 · 1490.4
- 17NAS overall
- #40 of 86
- API price (in / out)
- $1.25 / $4.25 per 1M tokens
- Closest rival
- Claude Opus 5 · 1491.1
- Cheaper alternative
- MiMo-V2.6-Pro: Text 1479.6, output $0.87 (80% cheaper)
- Data updated
- Oct 22, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 9 | Muse Spark 1.3 | 1494.7 | 48.1 | $4.25 | 113 |
| 10 | Muse Spark 1.2 | 1492.0 | 39.6 | $4.25 | – |
| 11 |  Claude Opus 5 | 1491.1 | 50.8 | $25.00 | – |
| 12 | Muse Spark 1.1This page | 1490.4 | 33.7 | $4.25 | – |
| 13 | Muse Spark | 1489.0 | 31.3 | – | – |
| 14 |  Gemini 3.7 Flash | 1488.9 | 39.1 | $3.75 | – |
| 15 |  Kimi K3 | 1488.1 | 43.6 | $15.00 | 39 |
More from Meta
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 2 | Muse Wonder | 1509.5 | 52.4 | $20.00 | 171 |
| 9 | Muse Spark 1.3 | 1494.7 | 48.1 | $4.25 | 113 |
| 10 | Muse Spark 1.2 | 1492.0 | 39.6 | $4.25 | – |
| 13 | Muse Spark | 1489.0 | 31.3 | – | – |
| – | Muse Spark Open | – | 38.9 | $4.25 | 138 |
| – | Muse Wonder Full | – | 55.8 | – | – |
Pricing
- Official API list price: $1.25 input and $4.25 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $2.00 per 1M tokens.
- Among 81 models with an output price, it is the #38 cheapest.
- The cheapest OpenRouter route charges $1.25 input / $4.25 output.
Sources & methodology
On the arena.ai Agents leaderboard, Muse Spark 1.1 has a task success rate of -6.60% (—, rank #40, 95% interval -7.25%–-5.95%).
- arena.ai Agents — agent task success rate, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does Muse Spark 1.1 do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Muse Spark 1.1 has a task success rate of -6.60% (—, rank #40, 95% interval -7.25%–-5.95%).
What rank is Muse Spark 1.1 right now?
Muse Spark 1.1 is #12 on our leaderboard of 69 scored models (Arena score 1490.4); its raw LMArena rank is #14.
What does Muse Spark 1.1 cost via API?
Input $1.25 / output $4.25 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $2.00 per 1M tokens.
How close is Muse Spark 1.1 to the models ranked next to it?
It is 0.7 points behind Claude Opus 5 (1491.1) and 1.4 points ahead of Muse Spark (1489.0); gaps smaller than the confidence interval (±4.2) are not significant.
Is Muse Spark 1.1 open source? Can it be self-hosted?
Muse Spark 1.1 is a closed model, available only via official APIs or hosted services.
What is the context length of Muse Spark 1.1?
1.05M (1,048,576 tokens, as listed on OpenRouter).
Muse Spark 1.1 vs Claude Opus 5: which is better?
On the LMArena Text leaderboard Muse Spark 1.1 scores 1490.4 and Claude Opus 5 scores 1491.1 (a 0.7-point gap, within the confidence interval, so not significant). Agent task success: Muse Spark 1.1 -6.60%, Claude Opus 5 8.09%. On price, Muse Spark 1.1 costs $4.25 and Claude Opus 5 $25.00 per 1M output tokens.
Is there a cheaper model close to Muse Spark 1.1?
Yes: MiMo-V2.6-Pro scores 1479.6 on the Text leaderboard (Muse Spark 1.1: 1490.4) and costs $0.87 per 1M output tokens, about 80% less than Muse Spark 1.1 ($4.25).
Where does the Muse Spark 1.1 data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Oct 22, 2026.