Flint benchmark details: 89.7 on SWE-Bench Pro v2, ahead of Qwen3.5 and Muse Glimmer
RichardSocher · x · 2026-10-22
Recursive published full benchmark comparisons for Flint (40B total/2.5B active) against local models on similar hardware. Flint leads its sparse MoE class on all six benchmarks: 54.9 on Terminal-Bench 2.1 (vs Qwen3.5's 38.7), 89.7 on SWE-Bench Pro v2, 74.2 on SWE-Bench Verified, 80.3 on LiveCodeBench v6, 89.2 on IFBench and 95.1 on IFEval. Dense models still lead some charts, but Flint runs far faster. Some competitor scores were measured internally.
Related event: Flint Benchmarks: Tops Sub-50B MoE, Runs at 131 tokens/s on M4 Pro(2 posts)→
More from Models
- Dev Quips Argon Is Good Because It Adds Things You Never Asked For — andrew_n_carr · 2026-10-22
- Six months later, the best AI costs 20× less — Tgoc · 2026-10-22
- Single RTX 5080 runs Qwen3.8-Flash-Next at 150 tok/s decode, 4.4K tok/s prompt — yehyakar · 2026-10-22
- Pichai on Gemini 4 Argon: even Google can't get enough AI compute — sundarpichai · 2026-10-22
- Flint founder recalls OpenAI Codex debate: local interactive coding vs cloud agents — josh_tobin_ · 2026-10-22
- Recursive launches Flint: an open 40B MoE model built for local agentic coding — josh_tobin_ · 2026-10-22