Muse Spark Openopen
Meta
45.1#199 of 427 overall
- Input / output
- US$ 1,25 / US$ 4,25 US$ per 1M tokens
- Context
- 1.0M tokens
- Release
- 10/15/2026 release date
- Speed
- 140 tok/s first token in 0.48 s
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| LiveBench weight 3 | 51.6 | 19% | LiveBench |
| AA Intelligence Index weight 3 | 24.7 | 40% | Artificial Analysis |
| Arena WebDev (Elo) weight 1 | 1526 | 61% | LMArena |
| Humanity's Last Exam weight 1 | 43.9 | 94% | Artificial Analysis |
| Terminal-Bench weight 1 | 8.1 | 69% | Artificial Analysis |
| GPQA Diamond | 89.0 | 87% | Artificial Analysis |
| Long-context reasoning | 78.3 | 81% | Artificial Analysis |
| LiveBench long agentic | 11.7 | 18% | LiveBench |
| LiveBench reasoning | 73.7 | 7% | LiveBench |
| LiveBench coding | 73.6 | 26% | LiveBench |
| LiveBench browser | 26.2 | 29% | LiveBench |
| LiveBench data analysis | 60.2 | 13% | LiveBench |
| LiveBench research | 80.3 | 68% | LiveBench |
| LiveBench design | 60.3 | 10% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 45.6 | #80 | LiveBench long agentic, Terminal-Bench |
| Coding | 45.7 | #69 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 59.2 | #149 | LiveBench reasoning, Humanity's Last Exam, GPQA Diamond |
| Data analysis | 31.4 | #28 | LiveBench data analysis |
| Research | 66.2 | #55 | LiveBench research, Long-context reasoning |
| Design | 40.3 | #80 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 39.5 | #23 | LiveBench browser |
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.