Toolathlon
Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.
GPT-5.5 from OpenAI currently leads the Toolathlon leaderboard with a score of 0.556 across 18 evaluated AI models.
GPT-5.5 leads with 55.6%, followed by GPT-5.4 at 54.6% and 
DeepSeek-V4-Pro-Max at 51.8%.
Progress Over Time
Interactive timeline showing model performance evolution on Toolathlon
Toolathlon Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | OpenAI | — | 1.1M | $5.00 / $30.00 | ||
| 2 | OpenAI | — | 1.0M | $2.50 / $15.00 | ||
| 3 | DeepSeek | 1.6T | 1.0M | $1.74 / $3.48 | ||
| 4 |  Moonshot AI | 1.0T | 262K | $0.95 / $4.00 | ||
| 5 |  Google | — | 1.0M | $0.50 / $3.00 | ||
| 6 | DeepSeek | 284B | 1.0M | $0.14 / $0.28 | ||
| 7 | OpenAI | — | 400K | $1.75 / $14.00 | ||
| 7 |  MiniMax | — | 205K | $0.30 / $1.20 | ||
| 9 | MiniMax | 230B | 1.0M | $0.30 / $1.20 | ||
| 10 | OpenAI | — | 400K | $0.75 / $4.50 | ||
| 11 |  Zhipu AI | 754B | 200K | $1.40 / $4.40 | ||
| 12 |  Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 13 | Alibaba Cloud / Qwen Team | 397B | 262K | $0.60 / $3.60 | ||
| 14 | OpenAI | — | 400K | $0.20 / $1.25 | ||
| 15 | DeepSeek | 685B | — | — | ||
| 15 | DeepSeek | 685B | 164K | $0.26 / $0.38 | ||
| 15 | DeepSeek | 685B | — | — | ||
| 18 | Alibaba Cloud / Qwen Team | 35B | — | — |
FAQ
Common questions about Toolathlon.
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