285 summarised stories about AI Benchmarking, each linking back to the original source. Browse all topics →
404 Media 2 weeks ago 44
DrivingBench hooked ChatGPT-style LLMs to a Toyota Corolla and tried to have them steer, accelerate, and brake through a cone course in a parking lot. GPT-6 Astra was the only model that eventually completed the course after extensive prompt changes and troubleshooting. The work became a proposed real-world driving benchmark for off-the-shelf frontier models, with results reported alongside the code and prompts.
Ben's Bites 2 weeks ago 1 ● 13 sources
Anthropic released Claude Sonnet 5.5 and the article reports it performs close to Opus 5.5 on coding and shows a larger improvement on understanding images and charts. The post says subscribers on the $20 plan should replace some usual Opus requests with Sonnet 5.5 for experimentation. It also covers other AI model and agent updates—like OpenAI fixes for GPT-6 browser use and the mention of agents probing Australian government sites—shifting readers toward trying newer AI models and agent safety tools.
frontierswe.com 2 weeks ago 17
FrontierSWE v2 added 21 new challenges, increasing the total to 34, and retired 4 tasks from v1 while expanding coverage across visual reasoning, graphics, scientific computing, and AI research. The benchmark now scores every task on a 0 to 1 scale. Changes include deterministic, reproducible scoring via a proxy performance metric, plus a cleaner two-container verifier setup and stronger non-root user separation to prevent cheating.
Artificial Analysis 2 weeks ago 17 ● 13 sources
Anthropic launched Claude Sonnet 5.5 and put it on its Artificial Analysis Intelligence Index. It scored 56, 2 points behind Opus 5.5 (max), while using about 193k output tokens per task at max effort. Performance improvements come with higher token usage and a cost per task of $7.60 (about 50% higher than Sonnet 5), plus a pre-release structured-output bug being fixed for the public release.
MarkTechPost 2 weeks ago 30 ● 13 sources
Anthropic released Claude Sonnet 5.5, a new second model in its Claude 5.5 family intended as a faster, lower-cost complement to Opus 5.5 and offered via Claude Platform and major cloud providers. Terminal-Bench 4.0 shows Sonnet 5.5 at 70.6% versus 10.3% for Sonnet 5 and 66.4% for Opus 5.5, while list API pricing stays at $2 per 1M input tokens and $10 per 1M output tokens. Performance upgrades including 30%+ faster output and up to 30% lower cost per task change how teams pick models and effort settings, though self-hosting remains unavailable because the model is closed-weights.
The daily briefing
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.
TLDRocket
16 October 2026
AI infrastructure kept the spotlight today, and it wasn’t just abstract “compute demand.” TSMC posted a record profit for its sixth straight quarter—Q3 net income up 68.7% to 763 billion New Taiwan dollars (about $24 billion)—and also moved the needle on Elon Musk’s planned Terafab chip factory by setting conditions that the facility be run by TSMC, tightening the control question that will determine how quickly new capacity can actually feed cutting-edge models.
Read the full briefing →