AA-Omniscience chart ranks 28 models on accuracy and hallucination
teortaxesTex · x · 2026-07-21
A new AA-Omniscience comparison chart ranks 28 of 446 models on two axes: accuracy and hallucination rate.
Key takeaways
- In accuracy, Claude 4 Opus, GPT-5.1, Sol, and GPT-5.5 lead the chart, with the top model at 61%.
- In hallucination rate, the best models sit in the 14%–29% range, while several lower-performing models climb above 80%.
- The post’s takeaway is that the benchmark suggests a strong relationship between scale, model family, and “omniscience”-style reliability, but also exposes large variance within and across vendors.
The author frames the chart as evidence that some models are much better at knowing what they know, while others are notably more prone to confident errors.
Related event: AA-Omniscience Chart Compares Accuracy and Hallucination Rates of 28 Models(2 posts)→
More from Models
- Week 3 of "Fable 5.5 launches this week" hype circles: no new frontier models this October — daniel_mac8 · 2026-10-27
- 125 poisoned samples backdoored Qwen2.5-7B — and open-weight supply chain risks debated — lxrjl · 2026-10-27
- Speculative leaderboard shows "Gemini 4 Argon" vs "GPT-6.1 Sol"; observer calls MiniMax parity suspicious — teortaxesTex · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27