Skip to main content
BenchLM
Advertise

Benchmark profile

MCP Atlas

A benchmark for tool-calling over Model Context Protocol integrations and external tools.

Data verified

Benchmark score on MCP Atlas — July 23, 2026

BenchLM mirrors the published score view for MCP Atlas. Muse Spark 1.1 leads the public snapshot at 88.1% , followed by Kimi K3 (84.2%) and Gemini 3.5 Flash (83.6%). BenchLM does not use these results to rank models overall.

1Closed

Muse Spark 1.1

Meta

muse-spark-1-1

88.1%
Overall 77.44Context 1M
2Closed

Kimi K3

Moonshot AI

kimi-3

84.2%
Overall 80.96Context 1.05M
3Closed

Gemini 3.5 Flash

Google

gemini-3-5-flash

83.6%
Overall 64.75Context 1M
29 modelsAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (29 models)

Score
1
Muse Spark 1.1Meta · Closed
88.1%
2
Kimi K3Moonshot AI · Closed
84.2%
3
Gemini 3.5 FlashGoogle · Closed
83.6%
4
Claude Opus 4.8Anthropic · Closed
82.2%
5
Claude Opus 4.7 (Adaptive)Anthropic · Closed
77.3%
6
GLM-5.2Z.AI · Open weight
76.8%
7
Qwen3.7 MaxAlibaba · Closed
76.4%
8
Kimi K2.7 CodeMoonshot AI · Open weight
76%
9
GPT-5.5OpenAI · Closed
75.3%
10
DeepSeek V4 Pro (High)DeepSeek · Open weight
74.2%
11
MiniMax M3MiniMax · Open weight
74.2%
12
InklingThinking Machines Lab · Open weight
74.1%
13
DeepSeek V4 Pro (Max)DeepSeek · Open weight
73.6%
14
Qwen3.7 PlusAlibaba · Closed
73.2%
15
GLM-5.1Z.AI · Open weight
71.8%
16
GPT-5.4OpenAI · Closed
70.6%
17
DeepSeek V4 ProDeepSeek · Open weight
69.4%
18
DeepSeek V4 Flash (Max)DeepSeek · Open weight
69%
19
DeepSeek V4 Flash (High)DeepSeek · Open weight
67.4%
20
DeepSeek V4 FlashDeepSeek · Open weight
64%
21
Qwen3.6-35B-A3BAlibaba · Open weight
62.8%
22
GPT-5.4 miniOpenAI · Closed
57.7%
23
GPT-5.4 nanoOpenAI · Closed
56.1%
24
Kimi K2.6Moonshot AI · Open weight
55.9%
25
Qwen3.6 PlusAlibaba · Closed
48.2%
26
Qwen3.5 397BAlibaba · Open weight
46.1%
27
Claude Opus 4.5Anthropic · Closed
42.3%
28
GLM-5Z.AI · Open weight
31.1%
29
Kimi K2.5Moonshot AI · Open weight
29.5%

The published MCP Atlas snapshot places Muse Spark 1.1 first at 88.1%. The third row is 4.5 points behind. The broader top-10 range is 13.9 points, so the table still separates the published systems.

29 models have been evaluated on MCP Atlas. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. MCP Atlas is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MCP Atlas

Year

2026

Tasks

Tool-integrated agent tasks

Format

Interactive tool-calling evaluation

Difficulty

Advanced tool use

OpenAI reports MCP Atlas as a tool-use benchmark that measures how well models work with MCP-backed systems and external tools.

Introducing GPT-5.4 mini and nano

BenchLM freshness & provenance

Version

MCP Atlas 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does MCP Atlas measure?

A benchmark for tool-calling over Model Context Protocol integrations and external tools.

Which model scores highest on MCP Atlas?

Muse Spark 1.1 by Meta currently leads with a score of 88.1% on MCP Atlas.

How many models are evaluated on MCP Atlas?

29 AI models have been evaluated on MCP Atlas on BenchLM.

Compare Top Models on MCP Atlas

Muse Spark 1.1 vs Kimi K3Kimi K3 vs Gemini 3.5 FlashGemini 3.5 Flash vs Claude Opus 4.8Claude Opus 4.8 vs Claude Opus 4.7 (Adaptive)
Last updated: July 23, 2026 · BenchLM version MCP Atlas 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.