A large-scale Scale AI benchmark for tool use with real MCP servers. It covers 36 servers, 220 tools, and 1,000 natural-language tasks that test tool discovery, cross-server orchestration, multi-step calls, and answer synthesis.
Browse the latest scores, model modes, release dates, and parameter sizes for MCP-Atlas.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Muse Spark 1.1 Thinking EnabledTools | 88.10 | 2026-07-09 | Unknown | Closed | |
 Kimi K3 Thinking Level · MaxTools | 84.20 | 2026-07-16 | 2800B | Free Commercial | |
 Gemini 3.5 Flash Thinking Level · HighTools | 83.60 | 2026-06-20 | Unknown | Closed | |
4 |  Claude Fable 5 Standard ModeTools | 83.30 | 2026-06-09 | Unknown | Closed |
5 | Muse Spark Standard ModeTools | 82.20 | 2026-04-08 | Unknown | Closed |
6 | Claude Opus 4.8 Deep Thinking ModeTools | 82.20 | 2026-05-28 | Unknown | Closed |
7 | Opus 4.7 Deep Thinking ModeTools | 79.10 | 2026-04-16 | Unknown | Closed |
8 |  Hy3 Thinking Level · HighTools | 79.10 | 2026-07-06 | 295B | Free Commercial |
9 | Gemini 3.1 Pro Preview Thinking Level · HighTools | 78.20 | 2026-02-20 | Unknown | Closed |
10 | Claude Opus 4.6 Deep Thinking ModeTools | 76.80 | 2026-02-05 | Unknown | Closed |
11 |  GLM 5.1 Standard ModeTools | 75.60 | 2026-03-27 | 75.4B | Free Commercial |
12 |  GPT-5.5 Thinking Level · Extra HighTools | 75.30 | 2026-04-23 | Unknown | Closed |
13 | Inkling Thinking EnabledTools | 74.10 | 2026-07-15 | 975B | Free Commercial |
14 | GPT-5.4 Thinking Level · Extra HighTools | 70.60 | 2026-03-05 | Unknown | Closed |
15 | Gemini 3.0 Pro (Preview 11-2025) Standard ModeTools | 70.30 | 2025-11-18 | Unknown | Closed |
16 | Opus 4.5 Thinking Level · HighTools | 69.80 | 2025-11-25 | Unknown | Closed |
17 | Claude Sonnet 4.6 Standard ModeTools | 69.50 | 2026-02-17 | Unknown | Closed |
18 | GPT-5.2 Thinking Level · Extra HighTools | 67.60 | 2025-12-11 | Unknown | Closed |
19 | Kimi K2.5 Standard ModeTools | 64.40 | 2026-01-27 | 1000B | Free Commercial |
20 | Gemini 3.0 Flash Standard ModeTools | 62.00 | 2025-12-17 | Unknown | Closed |
21 | Claude Sonnet 4.5 Thinking EnabledTools | 59.50 | 2025-09-30 | Unknown | Closed |
22 | GLM-4.7 Standard ModeTools | 58.10 | 2025-12-22 | 358B | Free Commercial |
23 | Gemini 3.1 Flash-Lite Thinking Level · HighTools | 57.10 | 2026-05-07 | Unknown | Closed |
24 | GPT-5.4 mini Thinking Level · Extra HighTools | 56.70 | 2026-03-17 | Unknown | Closed |
25 | GPT-5.1 Thinking Level · HighTools | 50.10 | 2025-11-12 | Unknown | Closed |
26 | o3-pro Standard ModeTools | 44.50 | 2025-06-10 | Unknown | Closed |
27 | Haiku 4.5 Standard ModeTools | 40.20 | 2025-10-15 | Unknown | Closed |
