benchmarks

Google’s Gemini 4 Pro appears on benchmark platform under disguised name

A model suspected to be Google's Alphabet Inc. next-generation flagship AI, Gemini 4 Pro, has appeared on the Arena benchmarking platform under the name "gemini-3.8-flash," according to developer reports that began circulating on September 17. The model, which carries the…

New benchmark finds quantum computers 100,000x short of scientific utility

Current quantum computers remain roughly five orders of magnitude below the computational capability needed to tackle recognized scientific problems, according to a new benchmarking study posted on the arXiv preprint server. The finding, from researchers at Sandia National Laboratories with…

Anthropic’s Claude models sweep top spots on SWE-bench coding benchmarks

Anthropic's Claude AI models hold the top positions across every major variant of the SWE-bench coding benchmark as of September 2026, with Claude Opus 5 reaching 96% on SWE-bench Verified and Claude Fable 5.1 scoring 81.2% on the more demanding…

GPT-6 Astra rolls out but trails Anthropic in independent benchmarks

OpenAI began rolling out GPT-6 Astra on September 3, calling it the "world's most intelligent and aligned model" with capabilities spanning browsing, coding, cybersecurity, and scientific reasoning. But independent benchmark evaluations published days later by Artificial Analysis place Astra second…