Copilot Fusion claims #1 on Terminal Bench 4.1 at less than half Claude Code's cost
imdigitalashish · x · 2026-11-20
imdigitalashish claims the top spot on Terminal Bench 4.1 at less than half the cost, scoring 5 points above Claude Code. The leaderboard screenshot shows Copilot Fusion (max) via GitHub Copilot at 71.2%±2.9% resolution rate ($2.8k cost), ahead of Opus 5.5 (max) with Claude Code at 65.8%±3.1% ($4.7k) and Fable 5.2 (max) at 65.8%; GPT-6.2, Gemini 4 and Kimi K3.1 Pro variants fill out the 60% band. Third-party claim, not yet independently verified.
More from coding & agent
- Is Haskell 'unsafe' too? A debate on types vs verification in the LLM era — satnam6502 · 2026-11-22
- Lessons from building a desktop AI agent that sees your screen and drives the mouse — SpeechAggravating453 · 2026-11-22
- MCP server checks if a pay-per-call x402 API is worth paying, from 24,766 real paid calls — biryaniAssasin · 2026-11-22
- Walmart and Muse to launch first agent-to-agent agentic commerce integration over MCP — AccBalanced · 2026-11-22
- scientific-toolkit: one MCP server fronting nine repos that refuses to fabricate results — Emergency-Tutor-7 · 2026-11-22
- Zero-degradation Strata tuning: fixing layer_split lifts decode ~10-15% and halves CPU expert misses — PathfinderTactician · 2026-11-22