GPT 6 Luna fails visual reasoning, worst Western model tester has seen in two years
Afinetheorem · x · 2026-09-25
New Blueprint-Bench results from Andon Labs: GPT 6 Sol slightly beats 5.6 Sol, Grok 4.7 slips vs 4.6, and GPT 6 Luna performs poorly. The tester says Luna's visual reasoning broke down badly — it misses image details and is the worst Western model he's benchmarked in two years, while Opus 5.5 was fantastic.
More from Models
- Do typos discomfort LLMs? Tokenization quirk sparks debate — menhguin · 2026-11-11
- MiniMax H3 hits 100 days open-source: 1,472 derivative models, 148M+ downloads — linoy_tsaban · 2026-11-11
- Meituan's LongCat-2.5 trends on Hugging Face as MoE multimodal model — meituan-longcat · 2026-11-11
- Fable 5.2 hands-on: great at well-defined hard problems, best since GPT 6 Astra — rachittshah · 2026-11-11
- The next AI vendor lock-in won't be the model API, it'll be the harness — Arindam_1729 · 2026-11-11
- Leaked: OpenAI's GPT-6.2 (codename betelgeuse) reportedly weighs in at ~15T tokens, drops Thursday — iruletheworldmo · 2026-11-11