When was Muse Spark released?

Muse Spark was released by Meta on Wednesday, Apr 8 2026.

Muse Spark was built by Meta. Develops the open-weight Llama series of models. Committed to open-source AI research.

What benchmark scores did Muse Spark get?

Muse Spark reports 17 tracked benchmark scores — Gray Swan IPI (k = 1): 2.9%; Gray Swan IPI (k = 10): 14.3%; Gray Swan IPI (k = 15): 16.5%; SWE-Bench Pro: 55%; SWE-Bench Verified: 77.4%; DeepSWE 1.1: 10%; Terminal-Bench 2.1: 67.3%; MCP Atlas: 82.2%; JobBench: 17%; Toolathlon-Verified: 49.4%; Humanity's Last Exam (with tools): 50.4%; ARC-AGI-2: 42.5%; GPQA Diamond: 89.5%; OSWorld-Verified: 53.3%; CharXiv Reasoning: 88.9%; BabyVision: 39.9%; MMMU: 80.4%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. It holds the best score among all models tracked here on CharXiv Reasoning.

Is Muse Spark open source?

No. Muse Spark is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

What came before and after Muse Spark?

Meta's previous tracked release was LLaMA 4 Maverick on Apr 5 2025, 368 days earlier. It was followed by Muse Spark 1.1 on Jul 9 2026.

Muse Spark

Released Apr 8 2026

Muse Spark is an AI model released by Meta on Wednesday, Apr 8 2026, 368 days after LLaMA 4 Maverick. Benchmark results (shown below) cover CharXiv Reasoning, Gray Swan IPI, SWE-Bench Pro, SWE-Bench Verified, DeepSWE 1.1, Terminal-Bench 2.1, and 9 more.

Benchmarks

Coding

SWE-Bench Pro

55%

#16 of 23

SWE-Bench Verified

77.4%

#22 of 57

DeepSWE 1.1

10%

#32 of 32

Terminal & CLI

Terminal-Bench 2.1

67.3%

#27 of 32

Agentic & tool use

MCP Atlas

82.2%

#4 of 11

JobBench

17%

#8 of 8

Toolathlon-Verified

49.4%

#9 of 9

OSWorld-Verified

53.3%

#26 of 28

Reasoning & science

Humanity's Last Exam

50.4%with tools

#24 of 45

ARC-AGI-2via BenchLM

42.5%

#29 of 34

GPQA Diamond

89.5%

#19 of 59

Multimodal

CharXiv Reasoning

88.9%

BabyVision

39.9%

#4 of 4

MMMU

80.4%

#4 of 7

Robustness

Gray Swan IPI

2.9%k = 1

14.3%k = 10

16.5%k = 15

k = 1

#5 of 13

k = 10

#5 of 13

k = 15

#6 of 14

Source: BenchLM, retrieved 11 July 2026. Other sources are identified on the linked benchmark pages.

Compare Muse Spark with

Muse Spark

Suggested comparisons

Muse SparkvsMuse Spark 1.3 Muse SparkvsGPT-6.1 Sol Muse SparkvsClaude Sonnet 5.5 Muse SparkvsGemini 4 Argon Muse SparkvsGrok 4.7 Muse SparkvsDeepSeek-V4.1-Flash Muse SparkvsMistral Large 4 Muse SparkvsKimi K3 Muse SparkvsGLM-5.3-Flash Muse SparkvsQwen3.8-Max-0902 Muse SparkvsNemotron 3.5 Lightning

About

Muse Spark, released April 8, 2026, was Meta's reset: a new model family retiring the Llama name a year after Llama 4, and — a sharp break with Meta's open-weights tradition — released as a closed model rather than a downloadable one. It debuted at 89.5% on GPQA Diamond, 80.4% on MMMU, and 77.4% on SWE-Bench Verified.

Its standout results were agentic: 82.2% on MCP Atlas for tool orchestration and 88.9% on CharXiv Reasoning, the best chart-understanding score of any model at release. Muse Spark 1.1 followed on July 9, 2026 with large gains across agentic benchmarks, including 20.0% on Harvey Legal Agent — the top published legal-work score on this tracker, and the coding-focused Muse Spark 1.2 arrived a month later.

Frequently asked questions

: Muse Spark was released by Meta on Wednesday, Apr 8 2026.
: Muse Spark was built by Meta. Develops the open-weight Llama series of models. Committed to open-source AI research.
: Muse Spark reports 17 tracked benchmark scores — Gray Swan IPI (k = 1): 2.9%; Gray Swan IPI (k = 10): 14.3%; Gray Swan IPI (k = 15): 16.5%; SWE-Bench Pro: 55%; SWE-Bench Verified: 77.4%; DeepSWE 1.1: 10%; Terminal-Bench 2.1: 67.3%; MCP Atlas: 82.2%; JobBench: 17%; Toolathlon-Verified: 49.4%; Humanity's Last Exam (with tools): 50.4%; ARC-AGI-2: 42.5%; GPQA Diamond: 89.5%; OSWorld-Verified: 53.3%; CharXiv Reasoning: 88.9%; BabyVision: 39.9%; MMMU: 80.4%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. It holds the best score among all models tracked here on CharXiv Reasoning.
: No. Muse Spark is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.
: Meta's previous tracked release was LLaMA 4 Maverick on Apr 5 2025, 368 days earlier. It was followed by Muse Spark 1.1 on Jul 9 2026.