Anthropic
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
This model is still tracked for research and discovery, but it is excluded from default public rankings until it returns to active status.
30.1
Quality Score
---
Arena ELO
Undisclosed
Parameters
1M
Context
Sign in to join the discussion
0
Downloads
0
Likes
Sep 2025
Released
Launches
1
Benchmarks
4
Research
2
General
8
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
We’re launching Claude Corps, a national fellowship program matching people early in their careers with US nonprofits. We'll teach 1,000 people to use Claude, and pay them to use AI to advance their hosts’ missions. https://t.co/QI6JmlAdSr
View source
SWE-Bench Verified resolved rate 73.8
SWE-Bench Verified resolved rate 73.8
View sourceLiveCodeBench pass@1 59.4 across 1055 tasks
View sourceGAIA score 25.2 from MAYA_v1
View sourceGAIA score 0.7 from agent404
View sourceNew in Claude Code: Artifacts. Interactive pages built from your session, like a PR walkthrough or a living project dashboard, shared with your team at a private link. Available in beta on Team and Enterprise plans. https://t.co/0NX9gNCaAs
New Frontier Red Team blog: Phase 2 of Project Fetch, where we test how well Claude can program a robodog. Opus 4.7, on its own, was ~20x faster than last year's best human team aided by Opus 4.1. (The robodog, alas, still failed to fetch a beach ball.) https://t.co/CgbBtRf85e
New in Claude Design: it stays on brand with your design system across projects, lets you edit directly on the canvas, syncs with Claude Code, and connects to more of the tools you already use. https://t.co/MK8YvLP8zV
Our latest economic research introduces a framework for tracking Claude Code as it scales. Who is using Claude Code, and what are they using it for? How is the value of tasks changing? And how much does domain expertise shape whether a session succeeds? https://t.co/IjjwQvrESo
We’re launching Claude Corps, a national fellowship program matching people early in their careers with US nonprofits. We'll teach 1,000 people to use Claude, and pay them to use AI to advance their hosts’ missions. https://t.co/QI6JmlAdSr
OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose a substantial attack surface that existing sandboxed evaluations fail to capture. To address this gap, we present the first real-world safety evaluation of OpenClaw and introduce the CIK taxonomy, which unifies an agent's persistent state into three dimensions, i.e., Capability, Identity, and Knowledge, for safety analysis. Our evaluations cover 12 attack scenarios on a live OpenClaw instance across four backbone models (Claude Sonnet 4.5, Opus 4.6, Gemini 3.1 Pro, and GPT-5.4). The results show that poisoning any single CIK dimension increases the average attack success rate from 24.6% to 64-74%, with even the most robust model exhibiting more than a threefold increase over its baseline vulnerability. We further assess three CIK-aligned defense strategies alongside a file-protection mechanism; however, the strongest defense still yields a 63.8% success rate under Capability-targeted attacks, while file protection blocks 97% of malicious injections but also prevents legitimate updates. Taken together, these findings show that the vulnerabilities are inherent to the agent architecture, necessitating more systematic safeguards to secure personal AI agents. Our project page is https://ucsc-vlaa.github.io/CIK-Bench.
LiveCodeBench pass@1 59.4 across 1055 tasks
GAIA score 25.2 from MAYA_v1