MCP Atlas
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
Gemini 3.5 Flash from Google currently leads the MCP Atlas leaderboard with a score of 0.836 across 18 evaluated AI models.
Gemini 3.5 Flash leads with 83.6%, followed by 
Claude Opus 4.7 at 77.3% and 
GPT-5.5 at 75.3%.
Progress Over Time
Interactive timeline showing model performance evolution on MCP Atlas
MCP Atlas Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Google | — | 1.0M | $1.50 / $9.00 | ||
| 2 | Anthropic | — | 1.0M | $5.00 / $25.00 | ||
| 3 | OpenAI | — | 1.1M | $5.00 / $30.00 | ||
| 4 |  Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 5 |  DeepSeek | 1.6T | 1.0M | $1.74 / $3.48 | ||
| 6 |  Zhipu AI | 754B | 200K | $1.40 / $4.40 | ||
| 7 | Google | — | 1.0M | $2.50 / $15.00 | ||
| 8 | DeepSeek | 284B | 1.0M | $0.14 / $0.28 | ||
| 9 | Zhipu AI | 744B | 200K | $1.00 / $3.20 | ||
| 10 | OpenAI | — | 1.0M | $2.50 / $15.00 | ||
| 11 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 12 | Anthropic | — | 1.0M | $5.00 / $25.00 | ||
| 13 | Anthropic | — | — | — | ||
| 14 | Anthropic | — | 200K | $3.00 / $15.00 | ||
| 15 | OpenAI | — | 400K | $1.75 / $14.00 | ||
| 16 | OpenAI | — | 400K | $0.75 / $4.50 | ||
| 17 | Google | — | 1.0M | $0.50 / $3.00 | ||
| 18 | OpenAI | — | 400K | $0.20 / $1.25 |
FAQ
Common questions about MCP Atlas.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions