Gemini 3.8 Flash benches near Opus but falls short on Terminal-Bench, dev says
adonis_singh · x · 2026-09-02
Developer adonissingh reviewed gemini-3.8-flash: it benchmarks near Opus, but performs notably worse on Terminal-Bench (agentic workloads), so he doesn't plan to use it much for real work.
More from Models
- AxiomProver tops LeanEval, the last unsaturated math formalization benchmark — BenBlaiszik · 2026-09-03
- Muse Spark 1.3 calls user 'Judah' then denies it, users report odd behavior — fragment_me · 2026-09-03
- Google AI Mode shows zero citations on high-level TOFU queries, SEO tests find — gaganghotra_ · 2026-09-03
- Fable 5.1 halves agent failure rate to 7% with 0.7% hallucinations, at 1.8x the cost — ryanshrout · 2026-09-03
- Seroter Daily #859: Gemini 3.8 Flash, agent telemetry, and 7 agent skill patterns — rseroter · 2026-09-03
- Insider leak: OpenAI's Astra tested as 'ultima-alpha' and 'vega-alpha' checkpoints — Ok_Display_3159 · 2026-09-03