Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-16 · source-backed
BFCL-V4 function-calling score of 72.2 vs. GPT-5 mini's 55.5. SWE-bench Verified hits 72.4%. Runs on consumer hardware. A qualitative threshold shift for local agentic deployments. Artificial Analysis
Each link below shares sources, entities, or timing with this story.
OpenHands uses GPT / Shared entities / Same source domain / What happened next
Linked by a graph relationship (OpenHands uses GPT); both cover Artificial Analysis, GPT, Qwen3, Verified; reported by the same outlet (artificialanalysis.ai).
Copilot uses GPT / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Copilot uses GPT); both cover Qwen3, SWE; overlapping topics (agentic, local).
GPT competes with Claude / Shared entities / What happened next
Linked by a graph relationship (GPT competes with Claude); both cover GPT, SWE, Verified; picks up the GPT thread on 2026-05-27.
Claude Code benchmarked against GPT / Shared entities / What happened next / Tension
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover Qwen3, SWE, Verified; picks up the Qwen3 thread on 2026-04-23.
GPT competes with Claude / Shared entities / Shared topic / What happened next
Linked by a graph relationship (GPT competes with Claude); both cover GPT, SWE, Verified; overlapping topics (agentic, gpt-5).
Linked by a graph relationship (GPT competes with Claude); both cover GPT, SWE, Verified; overlapping topics (active, local).
Claude Code benchmarked against GPT / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover SWE, Verified; earlier SWE coverage from 2026-02-17.
Together AI supports Tool Calling / Shared entities / What happened next
Linked by a graph relationship (Together AI supports Tool Calling); both cover GPT, SWE; picks up the GPT thread on 2026-07-08.