Inkling Hands-On Test Fails to Impress
emollick · x · 2026-07-16
After testing the new open-weight model Inkling, Emollick found its performance unstable in his tests: even when set to xHigh, it struggled to work reliably, with its chain of thought 'diverging' on simple requests.
Replies also noted that Inkling's current performance falls far short of some frontier Chinese open-source models, pointing out that it even failed the Lem Test, a test that has supposedly been passed by all frontier models since DeepSeek r1 / Sonnet 3.5.
Related event: New Open-Source Model Inkling Falls Short in Tests(2 posts)→
More from Models
- Benchmark scorecard pits GPT-5.6 Sol, Claude Fable 5, and Gemini 3.6 Flash — iruletheworldmo · 2026-07-22
- Google says Gemini 3.5 Pro is testing with partners and will go wide when ready — inductionheads · 2026-07-22
- ChatGPT merges Codex and adds GPT-5.6 tiers for knowledge work — jxnlco · 2026-07-22
- Dev Complains About Google's Fast Model Deprecation: Frequent Swaps Increase Maintainability Debt — Justin_Halford_ · 2026-07-22
- Elon Musk Responds to Gemini 3.6 Flash Release — elonmusk · 2026-07-22
- Google says Gemini 3.6 Flash can turn photos into custom creative tools — GeminiApp · 2026-07-22