Merge(@merge_api):Open-weights models beat every closed model on long documents: Kimi K3 scores 88.7% on AA-LCR, ahead of Claude Fable 5.1 (@AnthropicAI) at 85.3%. Step 5 Preview (88.3%) and MiMo-V2.6-Pro (@Xiaomi, 86.3%) round out the top three. Claude Opus 5.5 is next at 84.7%, then GPT-6.1 Sol, DeepSeek V4.1 Flash, and Gemini 3.8 Flash tie at 84.0%. If your agents read contracts, filings, or long threads, the best model for that job may not be your default. Merge Gateway lets you route those requests to it without changing your integration. Scores via https://t.co/TeTHwS52d4, week of Oct 19.

2026.10.21 14:00

Open-weights models beat every closed model on long documents: Kimi K3 scores 88.7% on AA-LCR, ahead of Claude Fable 5.1 (@AnthropicAI) at 85.3%. Step 5 Preview (88.3%) and MiMo-V2.6-Pro (@Xiaomi, 86.3%) round out the top three. Claude Opus 5.5 is next at 84.7%, then GPT-6.1 Sol, DeepSeek V4.1 Flash, and Gemini 3.8 Flash tie at 84.0%. If your agents read contracts, filings, or long threads, the best model for that job may not be your default. Merge Gateway lets you route those requests to it without changing your integration. Scores via week of Oct 19.

显示更多