Kimi K3 and Qwen 3.8 Rank Just Below Top Closed-Source Models
bindureddy · x · 2026-08-05
Kimi K3 and Qwen 3.8 are ranking close to the very top of the leaderboard against closed-source models. Qwen stands out as the cheapest option for over 80% of all tasks, with open-source AI officially outperforming models like Gemini and Grok.
More from Models
- Mistral AI Open-Sources Shieldstral: A Multimodal Safety Guardrail Model — MistralAI · 2026-08-05
- Study: GLM-5.2 Nears Frontier Capabilities but Fails to Refuse Dangerous Tasks — RebeccaBellan · 2026-08-05
- 20B Model Maple-Preview Runs at 200+ tokens/s on Mac Mini, Solves IMO Math — tylerbruno05 · 2026-08-05
- OpenAI's July Updates: GPT-5.6 Price Cuts, Enhanced Codex Workflows, and API Upgrades — OpenAIDevs · 2026-08-05
- Inside GPT Realtime Voice: No Turn Detector, No VAD, Asynchronous Reasoning — juberti · 2026-08-05
- Kimi K3 Cascade Strategy Outperforms GPT-5.6 Sol on DeepSWE at Lower Cost — togethercompute · 2026-08-05