株式会社オブライト

Articles tagged "SWE-bench"

3 articles

AI2026-04-17
Claude Opus 4.7 Complete Guide — SWE-bench 87.6%, Vision 98.5% & New xhigh Effort Mode [April 16, 2026 Release]
Released April 16, 2026, Claude Opus 4.7 achieves SWE-bench Verified 87.6%, Vision accuracy 98.5%, and introduces the new xhigh Effort Control — all at the same price as Opus 4.6. This guide covers every major upgrade to Anthropic's latest flagship model.
Claude Opus 4.7AnthropicSWE-bench
AI2026-04-10
GLM-5.1 Complete Guide — #1 SWE-bench Pro Open-Source LLM [April 2026]
GLM-5.1 by Z.ai (released April 7, 2026) is the first open-source LLM to top SWE-bench Pro at 58.4%, surpassing GPT-5.4 (57.7%) and Claude Opus 4.6 (57.3%). This guide covers its 744B/40B-active MoE architecture, MIT license, 8-hour autonomous task capability, and setup via Ollama.
GLM-5.1Z.aiSWE-bench
AI2026-04-10
MiniMax M2.5 Complete Guide — Lightning Attention Achieves 80.2% SWE-bench [2026]
MiniMax M2.5 achieves 80.2% on SWE-bench Verified using proprietary Lightning Attention in a 230B MoE model. Full breakdown of architecture, benchmarks, license terms, and setup instructions.
MiniMax M2.5SWE-benchLightning Attention