Muse Spark 1.2
Meta
77.6#19 of 427 overall
- Input / output
- US$ 1,25 / US$ 4,25 US$ per 1M tokens
- Context
- 1.0M tokens
- Release
- 08/05/2026 release date
- Weights
- Closed
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 4 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| Muse Spark | 04/08/2026 | 80.2 | #16 | — | 1474 |
| Muse Spark 1.1 | 07/16/2026 | 76.5 | #21 | — | 1478 |
| Muse Spark 1.2 | 08/05/2026 | 77.6 | #19 | — | 1483 |
| Muse Spark 1.3 | 09/02/2026 | 71.6 | #35 | 36.4 | 1491 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1483 | 93% | LMArena |
| Arena WebDev (Elo) weight 1 | 1534 | 62% | LMArena |
| Arena vision (Elo) weight 0.5 | 1304 | 88% | LMArena |
| Humanity's Last Exam weight 1 | 45.5 | 94% | Artificial Analysis |
| Terminal-Bench weight 1 | 7.1 | 68% | Artificial Analysis |
| GPQA Diamond | 90.4 | 91% | Artificial Analysis |
| Long-context reasoning | 79.0 | 82% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 59.1 | #38 | Terminal-Bench |
| Coding | 56.0 | #38 | Arena WebDev (Elo) |
| Reasoning | 78.4 | #20 | Humanity's Last Exam, GPQA Diamond |
| Research | 66.2 | #51 | Long-context reasoning |
| Design | 56.0 | #41 | Arena WebDev (Elo) |
| Chat | 71.5 | #14 | Arena text (Elo) |
| Vision | 68.8 | #14 | Arena vision (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.