1661 articles tagged with Benchmark
As video models enable longer and more realistic interactive experiences, maintaining a world consistent with its history becomes essential. This requires both preserving previousl...
Every "7 local models that replace Claude Code" list opens the same way: a table of SWE-bench scores,...
Meta's chart says Muse Wonder beats Opus 5.5. Artificial Analysis says 52 vs 58 at the same price. Settle it on your repo: two worktrees, one script.
"Aligning AI With Shared Human Values" introduces ETHICS, a 130K+ benchmark spanning five moral domains. Models show progress, but adversarial accuracy remains below 50%. #AIAlignm...
An agent calling your MCP server never sees your code. It sees tool names, descriptions and parameter...
Meta launched Muse Wonder and the subscriber-only Wonder Full, its first frontier AI models, positioning them as strong options for coding, legal, automation and personal-agent tas...
Sprix AI at 屿智同行 × 保研岛 — an open-source benchmark for AI agents in Baoyan advising and application planning.
Researchers introduced GeoSpatialBench to evaluate spatial cognition in multimodal large language models. The benchmark covers 28 relations using GeoJSON and map images.Source: arX...
SmartSalesBench is a new benchmark that evaluates large language model sales agents with resistant buyer personas over up to twenty conversational turns.Source: arXivhttps://arxiv....
A new benchmark introduces 5,525 document-grounded question-answer pairs over 415 open-source geopolitical and strategic intelligence reports to evaluate retrieval and generation s...
MisVisAgentBench is a new paired executable benchmark evaluating misleading visualizations in Web Agents. Replacing clean charts with misleading ones reduces the average task succe...
This is a submission for the Kaggle Benchmarking Challenge. Team: @g00ds0ul · @joyy-dev Benchmark:...
What I Benchmarked I tested whether the runtime around the model holds up: retrieval...
This is a submission for the Kaggle Benchmarking Challenge.* Why I built it I spent the...
Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development toward f...
This is a submission for the Kaggle Benchmarking Challenge. AI-assisted: I used AI to help develop...
A nightly prompt eval that collapses every failure into one boolean will blame the model for a cut-off response. The useful split is smaller than a full scoring platform and strict...
Your AI Follows Your Rules at Turn One. Does It Follow Them at Turn Forty? This is a...
Popular AI leaderboard Arena nearly doubles valuation to $3.1B valuation in 10 monthsThe company behind the popular LMArena leaderboard has raised $200 million led by Lightspeed an...
New "System One" decision model from the author of Laya: VegaML. Into the benchmark it went, on my M4 16 GB MacBook.How it works: a frozen Qwen3.5-0.8B reads the question, then a 1...
This is a submission for the Kaggle Benchmarking Challenge Table of Contents One Eye,...
What I Benchmarked A correct calculation can still answer the wrong question. Forty-eight...
This is a submission for the Kaggle Benchmarking Challenge. Urdu OCR has an unusually revealing...
Run it on your own GPU. No quantum hardware required. Two seasons, $1,000 prize each.#quantum #benchmark #opensource #machinelearning #software #coding #development #engineering #i...