Agentic benchmark
MCP Atlas leaderboard
Every model the catalog carries a published MCP Atlas value for, ranked by that value.
CategoryAgentic
MeasureInteractive tool-calling evaluation
TasksTool-integrated agent tasks
DifficultyAdvanced tool use
Published byIntroducing GPT-5.4 mini and nano
A benchmark for tool-calling over Model Context Protocol integrations and external tools.
MCP Atlas ranking
37 models with a published MCP Atlas value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Interactive tool-calling evaluation |
|---|---|---|---|
| 1 |  Muse Spark 1.1 | Meta | 88.1 |
| 2 |  Claude Opus 5 | Anthropic | 85.8 |
| 3 |  Kimi K3 | Moonshot AI | 84.2 |
| 4 |  Hy4 preview | Tencent | 83.7 |
| 5 |  Gemini 3.5 Flash | 83.6 | |
| 6 | Claude Opus 4.8 | Anthropic | 82.2 |
| 7 | OAOrnith-1.5-397B | Ornith AI | 80 |
| 8 | TMInkling-Small | Thinking Machines Lab | 79.6 |
| 9 | Claude Opus 4.7 (Adaptive) | Anthropic | 77.3 |
| 10 |  GLM-5.2 | Z.AI | 76.8 |
| 11 |  Qwen3.7 Max | Alibaba | 76.4 |
| 12 | Kimi K2.7 Code | Moonshot AI | 76 |
| 13 | Muse Glimmer 30B | Meta | 75.5 |
| 14 |  GPT-5.5 | OpenAI | 75.3 |
| 15 |  MiniMax M3 | MiniMax | 74.2 |
| 16 | TMInkling | Thinking Machines Lab | 74.1 |
| 17 |  DeepSeek V4 Pro 0813 | DeepSeek | 73.6 |
| 18 | Qwen3.7 Plus | Alibaba | 73.2 |
| 19 | GLM-5.1 | Z.AI | 71.8 |
| 20 | GPT-5.4 | OpenAI | 70.6 |
| 21 | OAOrnith-1.5-35B-A3B | Ornith AI | 70.2 |
| 22 | DeepSeek V4 Flash 0731 | DeepSeek | 69 |
| 23 |  Ling 3.0 Flash | InclusionAI | 65.5 |
| 24 | Qwen3.6-35B-A3B | Alibaba | 62.8 |
| 25 |  Solar Pro 4 | Upstage | 61.4 |
| 26 | Solar Open 2 | Upstage | 58.2 |
| 27 | GPT-5.4 mini | OpenAI | 57.7 |
| 28 | GPT-5.4 nano | OpenAI | 56.1 |
| 29 | Kimi K2.6 | Moonshot AI | 55.9 |
| 30 | OAOrnith-1.5-9B | Ornith AI | 54.2 |
| 31 | Qwen3.6 Plus | Alibaba | 48.2 |
| 32 | LLaDA2.2-flash | InclusionAI | 46.21 |
| 33 | Qwen3.5 397B | Alibaba | 46.1 |
| 34 |  LongCat-Flash-Lite-Sparse | Meituan | 45.6 |
| 35 | Claude Opus 4.5 | Anthropic | 42.3 |
| 36 | GLM-5 | Z.AI | 31.1 |
| 37 | Kimi K2.5 | Moonshot AI | 29.5 |
Evidence key: Observed
Rows are ordered by the value Introducing GPT-5.4 mini and nano published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.