Jev reranker cuts cost to 75% while lifting recruiting search matches by 30.64%
hardimanjames · x · 2026-10-01
Wrangle shares real-world results after adopting the Jev reranker from the TypesafeAI team: on actual recruiter searches with 200 candidates per round, matches per search improved by 30.64% at just 75% of the previous reranking cost.
The team also criticizes existing recruiting benchmarks, which typically measure precision across only 10 candidates — not representative of real sourcing workflows where recruiters screen hundreds of candidates per hire. A full benchmark will be released soon.
More from Models
- Fable 5.2 beats GPT-6 Astra: $7 in 2 min vs $98 in 24 min on same prompt — jradoff · 2026-11-16
- Qwen4 Max hands-on: matches GPT-6.1 Sol on agentic evals, trails on hard SWE at higher cost — haider1 · 2026-11-16
- Nous exec: avoid GPT 900k context variant — extra charges kick in past 272k — Teknium · 2026-11-16
- Rumor: Google's Gemini Argon and Carbon are both 12T-parameter models — oran_ge · 2026-11-16
- Qwen4 Max vs GPT-6.1 Sol at high reasoning effort: $0.0909 vs $0.132 — Angaisb_ · 2026-11-16
- FutureSim Q3: LLMs now genuinely improve from experience, Opus 5.5 tops at 50% — rickasaurus · 2026-11-16