Gemini 3.8 Flash scores 73.7% on DeepSWE, up 8.2% over 3.7 Flash at same cost
burny_tech · x · 2026-09-06
According to third-party benchmark results shared by datacurve, Gemini 3.8 Flash hits 73.7% on DeepSWE, an 8.2-point jump over Gemini 3.7 Flash.
- Cost stays the same, but the model uses more steps and output tokens
- The gains partly come from spending more tokens per task at flat pricing
- Third-party report for now; no detailed official release yet
More from Models
- Ornith 1.5 35B A3B beats Flint on hallucination and overthinking in user tests — BarberIcy366 · 2026-10-23
- Meta researcher: horrifying infra, not talent, is why OSS can't catch closed frontier — A_K_Nain · 2026-10-23
- TypeSafe's Jev: a "Decision Model" LLM That Returns Floats at $0.042/M Input Tokens — ariG23498 · 2026-10-23
- Microsoft's MAI-Base-2 scaling ladder pegs the L42 run at ~1.8×10^23 FLOPs — teortaxesTex · 2026-10-23
- Local model agentic coding benchmark: 27B matches 125B, tool-calling is the lever — Joralk_ · 2026-10-23
- NVIDIA open-sources PersonaPlex-7B, a full-duplex voice AI model that listens and talks simultaneously — solyarisoftware · 2026-10-23