Anthropic Lacks Standard Completions Endpoint; Fair Model Eval Needs Unified Harness
altryne · x · 2026-07-30
Commenting on current LLM evaluations, a developer pointed out that Anthropic lacks a standard OpenAI-like completions endpoint, preserving thinking processes and resembling OpenAI's Responses API. They suggested that a true apples-to-apples comparison requires a unified testing harness that extracts the best performance from any model.
Related event: Developers Question LLM Evaluation Fairness Due to API Inconsistencies(2 posts)→
More from Models
- Reflection AI open-sources Beam under Apache 2.0 with 40+ ecosystem partners — zhyncs42 · 2026-10-16
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection releases open MoE Beam-1.0: 501B total/23B active, 1M context, 3x fewer reasoning tokens — jacek2023 · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16