GPQA DiamondVerified
93.5%
GPQA Diamond (AA run)
Models / Meta
Muse Spark 1.3
Muse Spark · Released 2026-09-02
Meta's 2 Sep 2026 Muse Spark refresh. Same AA list as 1.2: $1.25 / $4.25 per 1M tokens, 1M context, text / image / video input. Ships in Muse Code and the Meta Model API.
Current Meta frontier for agentic coding and long-horizon tool use. Prefer sourced AA ledger rows over launch DeepSWE / vendor tables. Vals has no model page as of 5 Sep 2026.
Composite73
Context1M
Input / 1M$1.3
Output / 1M$4.3
Knowledge cutoffunpublished
Output speed190 t/s
Statusflagship
Family profile
Best published score in each covered benchmark family.
80/100 avg
- Reasoning
- 94
- Coding
- 59
- Agentic
- 84
- Long context
- 83
4 tested benchmark families
Editor's note
Vals model URL 404s as of 5 Sep 2026. Meta-reported DeepSWE and efficiency claims (~20% fewer tool calls, ~25% fewer tokens vs 1.2) stay vendor-cited. Editorial depth still needs a desk pass.Benchmark placements
Per-benchmark positions
Where Muse Spark 1.3 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 |
|---|---|---|---|---|---|
| SciCode | Coding | #8/ 97 | 59 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #12/ 184 | 94 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #12/ 186 | 49 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #16/ 184 | 83 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #17/ 167 | 84 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #18/ 195 | Artificial Analysis — output speed | 2026-09-05 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Muse Spark 1.3 shows up, it's highlighted.
ReasoningMuse Spark 1.3 · 94
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingMuse Spark 1.3 · 59
- 174
- 273
- 370
AgenticMuse Spark 1.3 · 84
- 191
- 289
- 389
Long contextMuse Spark 1.3 · 83
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for Muse Spark 1.3 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 83% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 93.5% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 48.7% | Artificial Analysis | 24 |
| SciCode | Coding | 58.8% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 84.27% | Artificial Analysis | 24 |
| AA output speed | Performance | 190 t/s | Artificial Analysis — output speed | 47 |
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 1.3 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 1.3. 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 1.3.
Reasoning
Humanity's Last ExamVerified
48.7%
HLE (AA run)
Coding
SciCodeVerified
58.8%
SciCode (AA run)
Agentic
Terminal-BenchVerified
84.27%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
83%
AA-LCR (AA run)
Performance
AA output speedVerified
190 t/s
Median output tokens/s (Meta API)
Changelog
Version history
- Muse Spark 1.3 available in Muse Code and the Meta Model API.
Sources
Where the numbers come from
- Meta Muse Spark 1.3 announcement· checked 2026-09-05
- Artificial Analysis Muse Spark 1.3· checked 2026-09-10
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 1.3?
Muse Spark 1.3 is a Meta model: Meta's 2 Sep 2026 Muse Spark refresh. Same AA list as 1.2: $1.25 / $4.25 per 1M tokens, 1M context, text / image / video input. Ships in Muse Code and the Meta Model API.
What is Muse Spark 1.3 for?
Current Meta frontier for agentic coding and long-horizon tool use. Prefer sourced AA ledger rows over launch DeepSWE / vendor tables. Vals has no model page as of 5 Sep 2026.
What does Muse Spark 1.3 cost?
Muse Spark 1.3 lists $1.3 input and $4.3 output per 1M tokens. Pricing last checked 2026-09-05.
How large is the Muse Spark 1.3 context window?
Muse Spark 1.3 publishes a 1M token context window.
What is the VerdictPal status of Muse Spark 1.3?
Muse Spark 1.3 carries Flagship 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.