News

Crowdsourced AI benchmarks have serious flaws, some experts say
Crowdsourced AI benchmarks like Chatbot Arena, which have become popular among AI labs, have serious flaws, some experts say.
OpenAI’s o3: AI Benchmark Discrepancy Reveals Gaps in Performance Claims
The FrontierMath benchmark from Epoch AI tests generative models on difficult math problems. Find out how OpenAI’s o3 and ...
OpenAI’s o3 AI model scores lower on a benchmark than the company initially implied
A discrepancy between first- and third-party benchmark results for OpenAI's o3 AI model is raising questions about the ...
Figuring out which AI model is right for you is harder than you think
AI models are numerous and confusing to navigate, but the benchmarks used to measure their performance are also challenging.
Digital Information World2d
Concerns Raised as OpenAI’s o3 AI Model Scores Major Discrepancy Between First and Third-Party Benchmark Results
OpenAI’s o3 model shows inflated benchmark results; real-world tests reflect performance far below initial FrontierMath ...
OpenAI is pushing for industry-specific AI benchmarks - why that matters
Benchmark performance results typically accompany the launch of every new AI model to showcase how well the models can ...
A tech investor says AI is already coming for jobs — and 2 professions should be very nervous
Victor Lazarte, a general partner at Benchmark, said AI is "fully replacing people." ...
Cryptopolitan on MSN2d
OpenAI’s o3 model falls short of its own benchmark claims
OpenAI’s newest LLM, o3, is facing scrutiny after independent tests found it solved a far fewer number of tough math problems ...
The Next Web1d
ESA and IBM launch AI model with ‘intuitive’ understanding of Earth
IBM and the European Space Agency (ESA) have launched TerraMind, billed as the best-performing AI model for Earth observation ...
Yahoo Finance3d
OpenAI's o3 AI model scores lower on a benchmark than the company initially implied
Epoch AI, the research institute behind FrontierMath, released results of its independent benchmark tests of o3 on Friday. Epoch found that o3 scored around 10%, well below OpenAI's highest ...