Meta•Rank #26

Muse Spark 1.2

Proprietarygeneralfastbudget

Leaderboard Score

53.5

Scale: 0 - 100

Throughput Speed

143 tps

Context Window

API Pricing / 1M

$1.25

Parameter Scale

Proprietary

Verified AI Radar & Benchmarks•8 Evaluated Metrics

Capability Radar & Benchmark Scores

Multi-Axis Capability Radar

Comparing Muse Spark 1.2 against Frontier Top 10 & Open-Source average

0 - 100 Scale

Muse Spark 1.2

Frontier Top 10 Avg

Open-Source Avg

Performance Vectors

Where Muse Spark 1.2 Leads

Coding & SWETop 10: 79.1% • OS: 47.6%

59.3%-19.8% vs Top 10

Reasoning & MathTop 10: 74.6% • OS: 46.6%

57.0%-17.6% vs Top 10

Agent & Tool AutomationTop 10: 71.2% • OS: 31.9%

48.5%-22.7% vs Top 10

Terminal & CLI ExecutionTop 10: 80.4% • OS: 47.6%

82.9%+2.5% vs Top 10

MMLU & Knowledge QATop 10: 50% • OS: 86.7%

66.9%+16.9% vs Top 10

Cyber & Security ExploitsTop 10: 87.8% • OS: 80.6%

50.8%-37.0% vs Top 10

All Verified Benchmark Evaluations

Direct Pass@1 and resolution rates across standardized evaluations.

OverallCodingReasoningAgenticTerminal

Featured Compute Platform

Run Benchmarks on Dedicated AI Clusters

Zero-cold-start inference endpoints with dedicated GPU instances.

Compare With Alternatives →

Executive Analysis & Verdict

Muse Spark 1.2 by Meta is a frontier agentic model scoring 53.5 overall with 1631 GDPVal-AA Elo, 59.3% on DeepSWE 1.1, and 82.9% on Terminal Bench 2.1.

Key Strengths & Highlights

•Rank #2 globally on GDPVal-AA v2 (1631 Elo) and Terminal Bench 2.1 (82.9% w/ Muse Code)
•High coding performance with 59.3% on DeepSWE 1.1 and 70.6% on Meta Internal Coding Bench
•Flexible pricing options including $0.10/$0.20 Contributor tier and 1M context

Limitations & Considerations

•Subject to standard provider rate limits and API quota

Recommended Workflows

Knowledge work automation, long-horizon terminal orchestration, and fast developer workflows

Architectural Overview & Capability Profile

Muse Spark 1.2 is developed by Meta AI as an advanced foundation model engineered for production enterprise applications, reasoning workflows, and autonomous problem-solving. On the comprehensive RankLLMs composite evaluation index, Muse Spark 1.2 registers an overall benchmark rating of 53.5 / 100.

Operating under a Proprietary license structure, Muse Spark 1.2 is served via high-throughput managed API endpoints designed for low-latency production queries.

Benchmark Performance & Real-World Utility

In standardized laboratory and real-world evaluation suites, Muse Spark 1.2 demonstrates calibrated proficiency across key performance vectors:

SWE-bench Verified Software Engineering (59.3%): Measures multi-file GitHub issue resolution. The model demonstrates practical capability in localizing source code bugs, synthesizing functional patches, and passing rigorous integration test matrices. For evaluation methodology, consult our SWE-bench Pro guide.
GPQA Diamond Scientific Reasoning (57%): Assesses graduate-level domain problem solving across physics, chemistry, and biology, minimizing hallucinations in multi-step deductive arguments. See our Humanity’s Last Exam benchmark analysis.
MATH-500 Competition Mathematics (57%): Evaluates formal mathematical problem solving and symbolic derivation, providing foundational logic for algorithmic computing.
Terminal-Bench Execution (82.9%): Reflects proficiency in interactive command-line environments, shell tool use, and automated DevOps scripting.
Code Arena Preference Rating (1631 Elo): Validates human developer satisfaction in blind side-by-side coding evaluations against contemporary alternatives.

Inference Latency & Cost Architecture

Token Context Window: 1.0M tokens, allowing large documents, multi-file codebases, and long conversation memories to be processed in a single context window.
Inference Speed: Reference throughput clocks at approximately 143 tokens/second, enabling responsive streaming in developer tools and interactive interfaces.
Commercial Pricing: API consumption is billed at $1.25 per 1M input tokens and $4.25 per 1M output tokens, offering predictable scaling for high-volume enterprise traffic.

Strengths, Limitations & Ideal Workflows

Primary Strengths

Rank #2 globally on GDPVal-AA v2 (1631 Elo) and Terminal Bench 2.1 (82.9% w/ Muse Code)
High coding performance with 59.3% on DeepSWE 1.1 and 70.6% on Meta Internal Coding Bench
Flexible pricing options including $0.10/$0.20 Contributor tier and 1M context

Known Considerations

Subject to standard provider rate limits and API quota

Recommended Use Cases

Knowledge work automation, long-horizon terminal orchestration, and fast developer workflows.

Compare with alternatives in the Model Comparison Engine
Compare global rankings on the AI Model Leaderboard
View complete platform index in our HTML Sitemap & Directory
Explore top coding models in our Best LLM for Coding Guide

Frequently Asked Questions About Muse Spark 1.2

What is Muse Spark 1.2 and who developed it?↓

Muse Spark 1.2 is a proprietary large language model developed by Meta. It ranks #26 on the RankLLMs composite leaderboard, ahead of 71% of the 85 models we track, with an overall score of 53.5 / 100.

Can Muse Spark 1.2 handle very long documents and codebases?↓

Muse Spark 1.2 supports a 1.0M-token input context window and generates about 143 tps tokens per second in our reference measurements and which is enough to hold entire repositories, long transcripts, or multi-document research sets in a single session..

How much does Muse Spark 1.2 cost per million tokens?↓

API pricing for Muse Spark 1.2 is $1.25 per 1M tokens - cheaper than 40% of priced models we track. Confirm the current rate on the provider's official pricing page before budgeting.

What is Muse Spark 1.2 best at?↓

Muse Spark 1.2 is strongest in Rank #2 globally on GDPVal-AA v2 (1631 Elo) and Terminal Bench 2.1 (82.9% w/ Muse Code); High coding performance with 59.3% on DeepSWE 1.1 and 70.6% on Meta Internal Coding Bench; Flexible pricing options including $0.10/$0.20 Contributor tier and 1M context. Full pillar-by-pillar numbers are in the benchmark tables above.

What should you watch out for with Muse Spark 1.2?↓

Known trade-offs include: Subject to standard provider rate limits and API quota. Weigh these against the strengths above for your specific workload.