#benchmark
Benchmark: 42 AI articles covering benchmark news, analysis, and research
Articles
The Cost of Saying Hello: An Empirical Study of Handshake⭐9
A first empirical benchmark of handshake overhead in AI agent protocols (MCP, A2A, ACP), measuring round trips, latency, wire bytes, and token cost across scena...
No Agenda, No Rush, No Leaving San Francisco: Benchmark’s⭐9
Benchmark’s partners explain their disciplined, partnership-driven model amid AI funding frenzies, discussing their $2 billion fundraise and focused investment ...
DeepSeek Launches V4.1-Flash-1017, Scores 77.0 on DeepSWE and⭐8
DeepSeek releases V4.1-Flash-1017, scoring 77.0 on DeepSWE with faster tasks and shorter outputs, plus open Search and Fetch APIs for developers.
Benchmark Admits AI Boom Is Eroding Venture Capital's Unwritten⭐9
Benchmark admits the AI boom is eroding venture capital's unwritten no-rivals rule, as competing AI startups share investors and board conflicts escalate.
Datalab Releases OmniParseBench: An Open OCR Benchmark With 16⭐9
Datalab’s OmniParseBench is an open OCR benchmark scoring parsers with 16,288 pass/fail tests across 2,937 pages, 92 languages.
TechCrunch Disrupt 2026: Day 2 Highlights — AI, Robotics, and⭐8
Explore Day 2 of TechCrunch Disrupt 2026 in San Francisco—AI, robotics, startup pitches, and exclusive ticket savings for founders and investors.
How to Define CPU and Software Stack Performance for Agentic AI⭐9
Agentic AI shifts performance to CPU orchestration, concurrency, and software stack efficiency. Learn the key metrics that define end-to-end agentic workload pe...
Pre-training, Reasoning, Benchmarking: X-ray Report Generation⭐8
This paper benchmarks X-ray report generation models on CheXpert Plus and proposes MambaXray-PRB, a framework using pre-training and multi-modal reasoning.
Tokka-Bench: A Standardized Framework for Evaluating Tokenizers⭐9
Tokka-Bench benchmarks seven BPE tokenizers across 100 natural and 20 programming languages, finding vocabulary allocation matters more than size.
Furientis Secures $25M from Benchmark to Mass-Produce Low-Cost⭐9
Furientis raises $25M from Benchmark to mass-produce low-cost missile interceptors, as defense tech investment gains momentum amid global conflicts.