Qwen 3.8 27B Beats Codex in Coding Benchmarks: Wins 8/13, Costs 1/3
tokenbender · x · 2026-08-16
A developer tested Qwen 3.8 27B on refactoring tasks against Codex 5.4. Qwen won 8 of 13 cases, Codex 5.5, with 2 overlaps and 2 neither. Qwen caught a simple race condition Codex missed, produced better output, and cost about 1/3 as much.
More from coding & agent
- Coding agents keep opening 3 stacked PRs per chat, and merging them is a nightmare — holdenmatt · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- Pattern MCP makes coding agents check existing components before writing new code — DonR954 · 2026-10-16
- Zero-keyframe procedural spider walks walls and ceilings using pure raycasts — yshan2u · 2026-10-16
- OpenCode v1.19.2 keeps 1.x installs off the 2.x update path — opencode-agent[bot] · 2026-10-16