ModelsSep 8, 2026 · 12:415 sources
Gemini 3.8 Flash and Muse Spark 1.3 Drop on Terminal Bench 4.0, Undermining GPT 6 Parity on TB 2.1
From huggingnews.com
Google released Gemini 3.8 Flash and Muse Spark 1.3 on Terminal Bench 4.0, where they underperformed GPT 6 parity on TB 2.1.
Read the sourceSign in to suggest
Sources
+ 4 more
- SUPPORT@semianalysis_“buy data from RL env startups that’s designed to mimic TB 2.1 tasks”x.com
- SUPPORT@semianalysis_“it was released 2 weeks ago”x.com
- SUPPORT@semianalysis_“Datacurve made a ton of money selling Google DeepSWE-shaped tasks”x.com
- SUPPORT@semianalysis_“The solution is more high quality private benchmarks”x.com
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today