Updated daily at 05:00 UTC
Ranking
Best AI models for Agentic tool use
Calling functions and MCP tools correctly over many turns, following policies, researching answers with search tools, and running long tasks on its own.
Ranked models
Based on 2 benchmarks
| Rank | Model | Company | Score | Coverage | Released |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | Google DeepMind | 52.4 | 2 of 2 | 19 Feb 2026 |
| 2 | Gemini 3 Pro Retired | Google DeepMind | 52.2 | 2 of 2 | 18 Nov 2025 |
| 3 | Claude Opus 4.5 | Anthropic | 49.1 | 2 of 2 | 24 Nov 2025 |
| 4 | Gemini 3 Flash | Google DeepMind | 49.0 | 2 of 2 | 17 Dec 2025 |
| 5 | Grok 4 Retired | SpaceXAI (xAI) | 45.5 | 2 of 2 | 9 Jul 2025 |
| 6 | Gemini 2.5 Pro | Google DeepMind | 43.1 | 2 of 2 | 25 Mar 2025 |
| 7 | GPT-5 Deprecated | OpenAI | 41.2 | 2 of 2 | 7 Aug 2025 |
| 8 | Claude Haiku 4.5 | Anthropic | 38.4 | 2 of 2 | 15 Oct 2025 |
| 9 | DeepSeek-R1 | DeepSeek | 35.0 | 2 of 2 | 20 Jan 2025 |
Not ranked yet
These models have independent or third-party results on too few of the 2 benchmarks to rank.
