#benchmark
Benchmark: 42 AI articles covering benchmark news, analysis, and research
Articles
ReviewBench: An Open Benchmark for AI Code Review⭐8
ReviewBench is an open benchmark for evaluating AI code reviewers on repository-level context retrieval, review quality, and fix quality to drive accountability...
EditHero: A New Benchmark for Long-Horizon Part-Level 3D Editing⭐9
EditHero introduces the first benchmark for long-horizon, part-level 3D editing, comparing non-agentic methods with LLM/VLM agents on instruction adherence and ...
Exa Launches Agent Ultra: A Subagent Swarm Deep Research API⭐9
Exa launches Agent Ultra, a subagent swarm deep research API for exhaustive list building. It outperforms Opus 5.5, GPT-6 Astra, and Perplexity Agent across fou...
Anthropic Unveils Opus 5.5: Lower Prices, Fable-Level⭐8
Anthropic releases Opus 5.5 with lower prices, faster performance, and strong safety safeguards, outpacing larger models on benchmarks and coding tasks.
Recognition, Simulation, and Refusal: A Contamination-Aware⭐9
PsyAgentBench separates genuine psychological biases in LLM agents from contamination-driven imitation, testing Asch conformity, anchoring, and more across 41,9...
Where Will the Next Breakout Startup Come From? Benchmark's Full⭐8
Benchmark’s full partnership joins TechCrunch Disrupt 2026 to discuss where the next breakout startups will come from and what founders are getting wrong.
Open Benchmark Evaluates AI Thermal Models for 2.5D and 3D ICs⭐9
A new open benchmark from UTS, TU Munich, and ShanghaiTech evaluates AI and machine-learning thermal models for 2.5D and 3D IC design.
MechReason: A New Benchmark for Multi-Image, Multi-Hop Reasoning⭐8
MechReason, a 12k-question benchmark from real mechanical engineering papers, tests multi-image, multi-hop reasoning in MLLMs across explanation, prediction, de...
Automating QUBO Formulation Generation from Natural Language⭐8
A multi-agent framework automatically converts natural-language problem descriptions into QUBO formulations, achieving 68% accuracy on the new QUBOBench benchma...
EvalDetectBench: A Benchmark for Measuring Evaluation Awareness⭐8
EvalDetectBench measures evaluation awareness in frontier LLMs, offering a benchmark pipeline to detect when models recognize assessments and improve evaluation...