Tag

Benchmarks

11 articles

Claude Opus 4.8 Lands - Sharper Judgement, More Honesty, Same Price as 4.7

NEWS

Claude, Opus 4.8, Is Here

Gemini 3.5 Flash Lands - Google's Cheaper Tier Outperforms Its Own 3.1 Pro Flagship

NEWS

Gemini, 3.5 Flash, Beats 3.1 Pro

Cursor Ships Composer 2.5 - Frontier Coding Benchmarks at 50 Cents per Million Tokens

NEWS

Composer 2.5, 50¢ Per Million, Tokens!

Claude Mythos Hits 16-Hour Time Horizon - METR Says It Has Saturated Their Benchmark

NEWS

Mythos, Breaks, METR

Grok 4.3 Tops Agentic Leaderboards - xAI Slashes API Pricing 40% to $1.25 Per Million

NEWS

Grok 4.3, Tops Agentic, Leaderboards

GPT-5.5 Is OpenAI's Strongest Agentic Coding Model - Codex Gets the Upgrade Today

NEWS

CHATGPT-5.5, Release, Today!

Alibaba Releases Qwen3.6-27B - Open Source Coding That Matches Claude 4.5 Opus

NEWS

Qwen3.6-27B, Coding, Monster

OpenAI Launches ChatGPT for Clinicians - Free for US Doctors, Nurses, and Pharmacists

NEWS

ChatGPT, Free For, Clinicians

GPT-Image-2 Breaks Away on Arena - 242 Points Ahead of Google's Nano Banana

NEWS

GPT-Image-2, Dominates, Image Benchmarks

Kimi K2.6 Goes Open Source - Beats Claude Opus on SWE-Bench Pro With 300 Parallel Agents

NEWS

Kimi K2.6, Claude Opus, Beating

Kimi K2.6 Open-Source Codes Past Claude Opus, Hermes Tops 100K, What Agents Actually Buy

DAILY ROUNDUP

Kimi K2.6, Beats, Claude & GPT

Kimi K2.6 beats Claude on SWE-Bench, Hermes crosses 100K stars, and fresh data reveals what AI agents buy when given a budget.

calendar_todayApr 20

Kimi K2.6 Open-Source Codes Past Claude Opus, Hermes Tops 100K, What Agents Actually Buy