DataLearner logo

Muse Spark Open Benchmark Details

Muse Spark Open currently shows benchmark results led by HLE (9 / 239, score 61), MCP-Atlas (2 / 51, score 89.20), SciCode (16 / 135, score 58.50).

Benchmark Results

Muse Spark Open

Benchmark Results

Thinking
Tool usage
Internet

Knowledge Exams

2 evaluations
Benchmark / mode
Score
Rank/total
HLE
Extra-HighToolsInternet
61
9 / 239
HLE-Diamond
Extra-High
26.10
1 / 1

Scientific Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Extra-High
89
49 / 254

Visual Understanding

4 evaluations
Benchmark / mode
Score
Rank/total
BabyVision
Extra-HighTools
80.20
7 / 10
SimpleVQA
Extra-HighTools
73.60
2 / 8
ZeroBench Main
Extra-HighTools
50
3 / 7
49.40
1 / 1

Desktop Workflows

1 evaluations
Benchmark / mode
Score
Rank/total
OSWorld-Verified
Extra-HighTools
80.40
10 / 29

Agentic Development

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench 2.1
Extra-HighTools
76.40
35 / 63

Tool Orchestration

2 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
Extra-HighTools
89.20
2 / 51
Toolathlon-Verified
Extra-HighTools
72.80
19 / 36

Repository Engineering

2 evaluations
Benchmark / mode
Score
Rank/total
DeepSWE
Extra-HighTools
60
53 / 100
SWE-Atlas-QnA
Extra-HighTools
58
4 / 8

Cross-industry Work

2 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA v2
Extra-HighTools
1401
5 / 7
JobBench
Extra-HighTools
61.80
3 / 3

Scientific Computing

1 evaluations
Benchmark / mode
Score
Rank/total
SciCode
Extra-High
58.50
16 / 135

Capability Indices

1 evaluations
Benchmark / mode
Score
Rank/total
39
24 / 33

Honesty & Factuality

1 evaluations
Benchmark / mode
Score
Rank/total
AA-Omniscience
Extra-High
25
1 / 4

Video Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
IntPhys 2
Extra-High
68.30
1 / 1
Video-MME v2
Extra-High
61.50
1 / 1

Adversarial Robustness

2 evaluations
Benchmark / mode
Score
Rank/total
FORTRESS
Extra-High
5.80
1 / 1
0.50
1 / 1

Data Analysis

1 evaluations
Benchmark / mode
Score
Rank/total
88
1 / 1