OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3

OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 with its latest API and two additional settings the-decoder.com

AI achieves first perfect score at International Math Olympiad

Artificial Intelligence Achieves Its First Perfect Score at the International Mathematical Olympiad (2026 Shanghai Competition) XenoSpectrum

Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing

We ran 904 DeepSWE rollouts on Kimi K3 and GPT-5.6 Sol. Sol leads pass@1; Kimi K3 wins pass@4 at 2.8x the solves per dollar, and routing between them reaches ~85.6%.

SciCodePile: 128GB benchmark for scientific code generation

Moonshot AI's Kimi K3 Beats Claude and GPT Rivals to Top a Coding Benchmark

Moonshot AI's Kimi K3 Beats Claude and GPT Rivals to Top a Coding Benchmark Startup Fortune

China’s Kimi K3 Is Out—And Beats Claude Fable and GPT 5.6 Sol on Key Benchmarks

China’s Kimi K3 Is Out—And Beats Claude Fable and GPT 5.6 Sol on Key Benchmarks Decrypt

OpenAI model defeats top programmers in coding competition

An OpenAI model crushed top human programmers at a world coding competition understandingai.org

OpenAI Launches GPT-5.6 AI Model Family - teleSUR English

OpenAI Launches GPT-5.6 AI Model Family teleSUR English

Anthropic Launches Claude Science AI Workbench For Scientists

Anthropic Launches Claude Science AI Workbench For Scientists Pulse 2.0

GLM-5.2 tops open weights models on intelligence index

Artificial Analysis: GLM-5.2 is the leading open weights model on Artificial Analysis' Intelligence Index, scoring 51, only behind Fable 5's 60, Opus 4.8's 56, and GPT-5.5's 55 — Z ai's GLM-5.2 is the new leading…

iOSWorld: A Benchmark for Personally Intelligent Phone Agents

Microsoft releases ASSERT framework for AI behavior testing

Ram Iyer / TechCrunch: Microsoft releases ASSERT, an open-source framework that lets developers generate and run AI behavior tests using natural-language descriptions — AI researchers and labs have advanced by…

Anthropic plans to release Mythos-class models in coming weeks

Madison Mills / Axios: Anthropic says it expects Mythos-class models to be available to all customers “in the coming weeks” following the development of stronger safeguards — Anthropic released Claude…

Claude and GPT-5.5 develop real browser exploits in new benchmark

Researchers at Carnegie Mellon University built a new benchmark that measures how far AI agents can go when exploiting real vulnerabilities in Google's V8 engine. Mythos leads GPT-5.5 by a wide margin but costs twelve…

Mythos Preview first to complete both AISI cyber ranges

AI Security Institute: Mythos Preview is the first AI model to complete both of AISI's cyber ranges, which measure models' cyberattack capabilities; GPT-5.5 solved only one of them — In February 2026, we internally…

DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Coding

We ran 900 DeepSWE rollouts on DeepSeek-V4 Flash and GPT-5.6 Luna. Luna leads pass@1 by 14 points; DeepSeek delivers 4.8x the solves per dollar.

OpenAI’s GPT-5.6 Tests Show Prompt-Injection Gains and Agent Risks

OpenAI’s GPT-5.6 Tests Show Prompt-Injection Gains and Agent Risks TechRepublic

ADMITBench framework evaluates safety of industrial LLM advisories

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

Show HN: Product analytics (and evals) for agent sessions on your MCP

Hi HN! We’re Theodore and Louis, founders of Armature (YC P26). We reconstruct the entire session behind the MCP tool calls you receive, including what the user asked their agent to do and what the agent thought.You…

Microsoft's cyber model beats Anthropic and OpenAI at half the cost

Microsoft In-House Cyber Model Beats Anthropic and OpenAI on Security Benchmark at Half Cost Tech Times

ScrambleToolBench: agents search exhaustively despite their map

Alibaba's Qwen3.8-Max tops Kimi K3, will open-source model

Luz Ding / Bloomberg: Alibaba says its 2.4T-parameter Qwen3.8-Max tops Kimi K3 on some benchmarks, and plans to release the open weights of Qwen3.8-Max and Qwen3.8-27B next week — Alibaba Group Holding Ltd…

DeepSeek’s Cheap Model Just Beat Its Own Flagship on Nine Benchmarks

DeepSeek’s Cheap Model Just Beat Its Own Flagship on Nine Benchmarks Times Tabloid

DeepSeek-V4-Flash Update

OmegaUse-OfficeVal tests LLM agents on complex office tasks

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

Opus 5 Tops New AI Leaderboard: What Developers Need to Know

Opus 5 Tops New AI Leaderboard: What Developers Need to Know SitePoint

Anthropic's Opus 5 blows past rivals on AI intelligence benchmark

Anthropic's Claude Opus 5 scored 30.2 percent on ARC-AGI-3, nearly quadrupling GPT-5.6 Sol's previous record of 7.8 percent. The benchmark's developers say the model independently formulated reflection equations, a…

Top AIs invent same fake PyPl and npm package names

Top AIs invent same fake PyPl and npm package names InfoWorld