GPQA DiamondVerified
88.4%
GPQA Diamond (AA run)
Models / Other
Muse Spark
Muse · Released 2026-01-01
Muse's tax-domain model. TaxEval v2 leader at 77.7% on Vals. Niche vertical — not a general-purpose frontier model.
Tax and compliance workflows only — do not use as a general research or coding model.
Composite62
Context128K
Input / 1M—
Output / 1M—
Knowledge cutoff2025-06-01
Statuslightweight
Family profile
Best published score in each covered benchmark family.
67/100 avg
- Reasoning
- 88
- Math
- 39
- Agentic
- 62
- Long context
- 78
4 tested benchmark families
Benchmark placements
Per-benchmark positions
Where Muse Spark places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| FrontierMath | Math | #9/ 15 | 39 | Epoch AI FrontierMath Tiers 1-3 (v2) CSV | 2026-08-15 |
| Humanity's Last Exam | Reasoning | #40/ 186 | 41 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #50/ 167 | 62 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #63/ 184 | 88 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #66/ 184 | 78 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #189/ 195 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Muse Spark shows up, it's highlighted.
ReasoningMuse Spark · 88
- 196
- 295
- 395
MathMuse Spark · 39
- 152
- 252
- 350
AgenticMuse Spark · 62
- 191
- 289
- 389
Long contextMuse Spark · 78
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for Muse Spark in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 78% | Artificial Analysis | 24 |
| AA output speed | Performance | 0 t/s | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 88.4% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 40.7% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 62.17% | Artificial Analysis | 24 |
| FrontierMath | Math | 39% | Epoch AI FrontierMath Tiers 1-3 (v2) CSV | 68 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where Muse Spark sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Muse Spark. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for Muse Spark.
Reasoning
Humanity's Last ExamVerified
40.7%
HLE (AA run)
Math
FrontierMathVerified
39%
FrontierMath Tiers 1-3 (v2) best Epoch run
Agentic
Terminal-BenchVerified
62.17%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
78%
AA-LCR (AA run)
Performance
AA output speedVerified
0 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Vals TaxEval v2· checked 2026-06-09
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Muse Spark?
Muse Spark is a Other model: Muse's tax-domain model. TaxEval v2 leader at 77.7% on Vals. Niche vertical — not a general-purpose frontier model.
What is Muse Spark for?
Tax and compliance workflows only — do not use as a general research or coding model.
What does Muse Spark cost?
Muse Spark lists — input and — output per 1M tokens. Pricing last checked 2026-06-09.
How large is the Muse Spark context window?
Muse Spark publishes a 128K token context window.
What is the VerdictPal status of Muse Spark?
Muse Spark carries Lightweight status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.