# MCP Atlas leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/agentic-mcp-atlas

Every model the catalog carries a published MCP Atlas value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Interactive tool-calling evaluation |
| Tasks | Tool-integrated agent tasks |
| Difficulty | Advanced tool use |
| Published by | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |

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

## MCP Atlas ranking

55 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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Muse Spark Open](https://modelchoice.dev/models/muse-spark-open) | Meta | 89.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Muse Spark 1.1](https://modelchoice.dev/models/muse-spark-1-1) | Meta | 88.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 85.8 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Step 5 Preview](https://modelchoice.dev/models/step-5-preview) | StepFun | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Inkling 2 Small](https://modelchoice.dev/models/inkling-2-small) | Thinking Machines Lab | 85 | Observed 2026-11-21 · source benchlm:models |
| 6 | [ERNIE 5.5 Flash Preview](https://modelchoice.dev/models/ernie-5-5-flash-preview) | Baidu | 84.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 84.2 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Hy4 preview](https://modelchoice.dev/models/hy4-preview) | Tencent | 83.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 83.6 | Observed 2026-11-21 · source benchlm:models |
| 10 | [LongCat-2.5](https://modelchoice.dev/models/longcat-2-5) | Meituan | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Ling 3.1 Flash](https://modelchoice.dev/models/ling-3-1-flash) | InclusionAI | 83 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Inkling 2 Mini](https://modelchoice.dev/models/inkling-2-mini) | Thinking Machines Lab | 82.7 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 82.2 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Beam 1.0 501B-A23B FP8](https://modelchoice.dev/models/reflection-beam-fp8) | Reflection AI | 81.5 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Beam 1.0 501B-A23B](https://modelchoice.dev/models/reflection-beam) | Reflection AI | 80.8 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Beam 1.0 501B-A23B NVFP4](https://modelchoice.dev/models/reflection-beam-nvfp4) | Reflection AI | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Ornith-1.5-397B](https://modelchoice.dev/models/ornith-1-5-397b) | Ornith AI | 80 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Inkling-Small](https://modelchoice.dev/models/inkling-small) | Thinking Machines Lab | 79.6 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 77.3 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Claude Opus 4.7 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-7-max) | Anthropic | 77.3 | Last good 2026-11-18 · source benchlm:models |
| 21 | [GLM-5.2](https://modelchoice.dev/models/glm-5-2) | Z.AI | 76.8 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 76.4 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Kimi K2.7 Code](https://modelchoice.dev/models/kimi-k2-7-code) | Moonshot AI | 76 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Ling 3.0 Flash Sante](https://modelchoice.dev/models/ling-3-0-flash-sante) | InclusionAI | 75.6 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Muse Glimmer 30B](https://modelchoice.dev/models/muse-glimmer-30b) | Meta | 75.5 | Observed 2026-11-21 · source benchlm:models |
| 26 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 75.3 | Observed 2026-11-21 · source benchlm:models |
| 27 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Inkling](https://modelchoice.dev/models/inkling) | Thinking Machines Lab | 74.1 | Observed 2026-11-21 · source benchlm:models |
| 29 | [DeepSeek V4 Pro](https://modelchoice.dev/models/deepseek-v4-pro) | DeepSeek | 73.6 | Observed 2026-11-21 · source benchlm:models |
| 29 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 73.6 | Last good 2026-11-18 · source benchlm:models |
| 31 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 73.2 | Observed 2026-11-21 · source benchlm:models |
| 32 | [GLM-5.1](https://modelchoice.dev/models/glm-5-1) | Z.AI | 71.8 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Ripple-65B Preview](https://modelchoice.dev/models/ripple-65b-preview) | Ricursive Intelligence | 71.67 | Observed 2026-11-21 · source benchlm:models |
| 34 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Ornith-1.5-35B-A3B](https://modelchoice.dev/models/ornith-1-5-35b-a3b) | Ornith AI | 70.2 | Observed 2026-11-21 · source benchlm:models |
| 36 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 69 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Ling 3.0 Flash](https://modelchoice.dev/models/ling-3-0-flash) | InclusionAI | 65.5 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 62.8 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Spark-X2.6-4B](https://modelchoice.dev/models/spark-x2-6-4b) | SparkLLM | 62.4 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Solar Pro 4](https://modelchoice.dev/models/solar-pro-4) | Upstage | 61.4 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Solar Open 2](https://modelchoice.dev/models/solar-open-2) | Upstage | 58.2 | Observed 2026-11-21 · source benchlm:models |
| 42 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 57.7 | Observed 2026-11-21 · source benchlm:models |
| 43 | [GPT-5.4 nano](https://modelchoice.dev/models/gpt-5-4-nano) | OpenAI | 56.1 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 55.9 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Nemotron 3.5 Bolt 74B-A9B BF16](https://modelchoice.dev/models/nemotron-3-5-bolt-74b-a9b-bf16) | NVIDIA | 55.6 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Ornith-1.5-9B](https://modelchoice.dev/models/ornith-1-5-9b) | Ornith AI | 54.2 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Nemotron 3.5 Bolt 74B-A9B](https://modelchoice.dev/models/nemotron-3-5-bolt-74b-a9b) | NVIDIA | 52.2 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 48.2 | Observed 2026-11-21 · source benchlm:models |
| 49 | [LLaDA2.2-flash](https://modelchoice.dev/models/llada2-2-flash) | InclusionAI | 46.21 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 46.1 | Observed 2026-11-21 · source benchlm:models |
| 51 | [LongCat-Flash-Lite-Sparse](https://modelchoice.dev/models/longcat-flash-lite-sparse) | Meituan | 45.6 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 42.3 | Observed 2026-11-21 · source benchlm:models |
| 53 | [LFM3-1.7B](https://modelchoice.dev/models/lfm3-1-7b) | LiquidAI | 32.57 | Observed 2026-11-21 · source benchlm:models |
| 54 | [GLM-5](https://modelchoice.dev/models/glm-5) | Z.AI | 31.1 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 29.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
