Benchgen

MCP-Atlas — Results

RankModelScore
1muse-spark-1-290.3
2muse-spark-open-816b-a42b89.2
3muse-spark88.1
4kimi-k384.2
5hy4-preview83.7
6claude-fable-583.3
7gpt-5-6-sol81.8
8beam-1-0-501b-a23b80.8
9ornith-1-5-397b80
10gemini-3-1-pro78.2
11glm-5-277.8
12muse-glimmer75.5
13gpt-5-575.3
14inkling74.1
15qwen3-6-plus74.1
16deepseek-v4-pro73.2
17ripple-65b-preview71.67
18ornith-1-5-35b-a3b70.2
19kimi-k2-668.1
20gpt-5-467.2
21kimi-k2-564
22qwen3-6-35b-a3b62.8
23claude-opus-4-662.7
24spark-x2-6-4b62.4
25claude-opus-4-562.3

MCP-Atlas — Evaluations

1 phaseActive

No evaluations yet for this benchmark.