Gemini 3.8 Flash benchmarks reportedly beat Opus 5 and Sol 5.6 on most tests
tkipf · x · 2026-09-02
Gemini 3.8 Flash's official benchmarks are out and it reportedly beats Opus 5 and Sol 5.6 on most of the benches shown. Prominent ML researcher Matthias Fey (tkipf, of GraphSAGE fame) chimes in that it's a good model and still insanely fast. Numbers come from a benchmark screenshot; treat as reported rather than independently verified.
Related event: Gemini 3.8 Flash Appears to Be Shadow-Launching Ahead of Imminent Release(33 posts)→
More from Models
- Google ships Gemini 3.8 Flash, third Flash update in 6 weeks, boosting agentic and coding skills — reach_vb · 2026-09-03
- Google launches Gemini 3.8 Flash Cyber security model alongside Fairwind Program for defenders — GoogleAI · 2026-09-03
- Matt Shumer: slow AI releases aren't a wall — safety clearance is the bottleneck, wave of frontier models imminent — mattshumer_ · 2026-09-03
- Early Gemini 3.8 testing suggests Gemma 4.5 will be very good — andrew_n_carr · 2026-09-03
- OpenAI's Astra model checkpoints spotted: vega-alpha and ultima-alpha in testing — koltregaskes · 2026-09-03
- Code Arena launches WebDev Pareto frontier to rank AI models by quality vs price — arena · 2026-09-03