GPT-OSS distilled from DeepSeek scores 83.61% without censorship transfer
An open-weight 20B model distilled from DeepSeek V4 Flash with an 8k token budget scores 83.61% on FinanceReasoning, beating Kimi K3 (81.93%) and Inkling (65.13%).
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Pokee-Isaac 28B V0 offers 10M-token context and tool use
- Goodfire Silico helps frontier AI research on vision models
- Codex creates CAD design for lost coffee grinder lid
- Not Diamond launches Code model router for coding agents
- Opus 4.8 quality at half the cost touted for agent infrastructure