Muse Spark 1.3 Benchmark Details

Muse Spark 1.3 currently shows benchmark results led by DeepSWE (1 / 34, score 75.40), Terminal-Bench 2.1 (2 / 49, score 88.80), AutomationBench (2 / 13, score 49.40).

Benchmark Results

Muse Spark 1.3

Benchmark Results

AI Agent - Tool Usage

3 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench 2.1

Thinking Level · MaxTools

88.80

2 / 49

OSWorld 2.0

Thinking Level · MaxTools

66.90

3 / 8

AutomationBench

Thinking Level · MaxTools

49.40

2 / 13

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

DeepSWE

Thinking Level · MaxTools

75.40

1 / 34

Productivity Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

GDPval-AA v2

Thinking Level · MaxToolsInternet

1754

5 / 25

AI Agent - Information Search

1 evaluations

Benchmark / mode

Score

Rank/total

DeepSearchQA

Thinking Level · MaxToolsInternet

89.40

2 / 3

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Job Bench

Thinking Level · MaxTools

64.90

1 / 5

Compare with other models