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%. Scores are the figures published at release by Meta. It holds the best score among all models tracked here on CharXiv Reasoning.

Is Muse Spark open source?

No. Muse Spark is a proprietary 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%

#26 of 26

Terminal & CLI

Terminal-Bench 2.1

67.3%

#26 of 30

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

#22 of 42

ARC-AGI-2

42.5%

via BenchLM

#18 of 21

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

#5 of 13

Source: BenchLM, retrieved 11 July 2026. Every other score here is the figure the lab published at launch.

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 proprietary 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.

Compare Muse Spark with

Muse Spark

Suggested comparisons

Muse SparkvsMuse Spark 1.3 Muse SparkvsGPT-6 Astra Muse SparkvsClaude Fable 5.1 Muse SparkvsGemini 3.8 Flash Muse SparkvsGrok 4.6 Muse SparkvsDeepSeek-V4.1-Flash Muse SparkvsMistral Medium 3.5 Muse SparkvsKimi K3 Muse SparkvsGLM-5.3-Flash Muse SparkvsQwen3.8-Max-0902 Muse SparkvsNemotron 3.5 Lightning

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%. Scores are the figures published at release by Meta. It holds the best score among all models tracked here on CharXiv Reasoning.
: No. Muse Spark is a proprietary 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.