Gemini 3.8 Flash reportedly out: 89.4% on Terminal-Bench 2.1, 73.7% on DeepSWE
ChrisGPT · x · 2026-09-03
ChrisGPT reports (unofficial) that Gemini 3.8 Flash is out, scoring 89.4% on Terminal-Bench 2.1—noting the benchmark is outdated now that Terminal-Bench 4 exists—and 73.7% on DeepSWE verified, strong for a Flash-tier model. Screenshot included. Third-party claim, unconfirmed.
Related event: Gemini 3.8 Flash benchmarks leak ahead of rumored launch(43 posts)→
More from Models
- Gemini 3.8 Flash Is Now Available in Cursor — YangsiboHuang · 2026-09-03
- Researcher: model Fable plainly obviates a CS college education as a professor — generativist · 2026-09-03
- Dev: hard to trust frontier labs' data promises, another reason to use OSS models — adityaag · 2026-09-03
- NVIDIA tops Hugging Face open-source repos with 500+ added, ahead of Alibaba and Tencent — Sam_Witteveen · 2026-09-03
- GLM 5.3 at 200+ TPS builds a full web page in 37 seconds, unedited video — nutlope · 2026-09-03
- Same-prompt test: fable 5.1 vs sol 5.6 generating a realistic three.js waterfall — majidmanzarpour · 2026-09-03