Cognition's FrontierCode 2: Opus 5.5 and GPT-6 Astra lead; Chinese OSS models lag at 17%
scaling01 · x · 2026-10-28
Cognition's FrontierCode 2 price-vs-performance leaderboard is dominated by OpenAI and Anthropic models, with Grok 4.7 xhigh the lone exception at #20 (28.6%). Opus 5.5 max scores 45.5% at $12.82/task and GPT-6 Astra max 42.8% at $6.68; GPT-6.1 Sol leads cost efficiency at 39% for $1.03/task. Chinese OSS models Kimi K3 and GLM 5.3 score just 17%, DeepSeek V4.1 Flash ranks 52nd, and American OSS models Beam and Inkling trail further at 3%.
More from Models
- Open-weight models now hold 72% of OpenRouter tokens as Tim Shi bets enterprises will own their intelligence — thursdai_pod · 2026-10-28
- Google launches Genie 4: its most realistic interactive world model with native audio and real-time steering — BorisMPower · 2026-10-28
- EmbeddingGemma 2 runs real-time embeddings on a MacBook CPU alone: 20ms text, 100ms images — generativist · 2026-10-28
- Google Gemma rounds up EmbeddingGemma 2 community projects, from WebGPU photo search to Apple Silicon — GlennCameronjr · 2026-10-28
- DeepSeek says "I'm ChatGPT" in identity test, resurfacing distillation allegations — ResonantFork · 2026-10-28
- Developer chats with a lamp fully locally using the new LFM3-Audio model — ngxson · 2026-10-28