Gemini 2.5 Pro: Expanding Managed Agents in Gemini API: background tasks, remote MCP and more

Google DeepMind released Gemini 2.5 Pro on March 25, 2025, expanding managed agents in the Gemini API with background tasks and remote MCP support. The model ranks in the top 50 on agentic, reasoning, knowledge, math, and multilingual benchmarks, and scores 17.8 on Humanity's Last Exam.

Google DeepMind /providers/google Gemini 2.5 Pro Is Gemini 2.5 Pro out yet? Yes. How we confirmed it Released via official access March 25, 2025 at 12:00 AM UTC Waiting for Google DeepMind's next model? One click creates your free account or signs you into an existing one and turns on alerts for Google DeepMind releases. There's no password to set, and you can unsubscribe any time. Benchmarks Agentic 32 Gemini 2.5 Pro · via BenchLM.ai · captured Jul 3, 2026 · source https://benchlm.ai/embed/leaderboard?category=agentic 57.1 Reasoning 38 Gemini 2.5 Pro · via BenchLM.ai · captured Jul 3, 2026 · source https://benchlm.ai/embed/leaderboard?category=reasoning 58.7 Knowledge 44 Gemini 2.5 Pro · via BenchLM.ai · captured Jul 3, 2026 · source https://benchlm.ai/embed/leaderboard?category=knowledge 66.3 Math 30 Gemini 2.5 Pro · via BenchLM.ai · captured Jul 3, 2026 · source https://benchlm.ai/embed/leaderboard?category=math 73.2 MultimodalGrounded 13 Gemini 2.5 Pro · via BenchLM.ai · captured Jul 3, 2026 · source https://benchlm.ai/embed/leaderboard?category=multimodalGrounded 85.2 Multilingual 33 Gemini 2.5 Pro · via BenchLM.ai · captured Jul 3, 2026 · source https://benchlm.ai/embed/leaderboard?category=multilingual 68.9 Humanity's Last Exam Gemini 2.5 Pro Preview May 06 2025 · via Epoch AI · captured Jul 3, 2026 · source https://epoch.ai/benchmarks/hle 17.8 LM Arena 55 gemini-2.5-pro · via LM Arena · 124,527 votes · captured Jul 3, 2026 · source https://lmarena.ai/leaderboard 1445.66 Sourced metrics mirrored with attribution — not community sentiment. Data from BenchLM.ai https://benchlm.ai . Data from Epoch AI, “AI Benchmarking Hub” https://epoch.ai/benchmarks CC BY 4.0 . Vibe rating How this model actually feels to use, rated by the people here. No vibe ratings yet. Be the first. Sign in /signin to rate this model. Model Pulse How is this model behaving today? One check-in per person per day: the running record of “did they nerf it”. Resets at midnight UTC. No check-ins yet today. Be the first to log how this model is behaving. Sign in /signin Community consensus An AI summary of the public comments here. Not a sourced fact. Not enough public feedback yet to summarize. Add a comment to help build the picture. Compare Gemini 2.5 Pro with another model → /compare?models=gemini-2-5-pro Also waiting on: ChatGPT 5.6 /models/chatgpt-5-6 , Gemini 3.5 Pro /models/gemini-3-5-pro , Claude Fable 5.1 /models/claude-fable-5-1 , Claude Mythos 5.1 /models/claude-mythos-5-1 Comments Missing a model, or wishing OutYet did something it doesn't? Tell us what to build /submit .