Benchmarks · knowledge
AA-Omniscience v1 Non-hallucination
AA-Omniscience v1: one minus AA's hallucination rate; not the combined Omniscience Index.
137 models · 268 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Argon high
All results
268 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Gemini 4 Argon | high | 84.9% |
| 2 | Grok 4.3 | medium | 83.1% |
| 3 | Grok 4.3 | low | 82.6% |
| 4 | Qwen 3.8 27B | none | 81.9% |
| 5 | MiniMax M3 | 81.6% | |
| 6 | Grok 4.6 | medium | 76.0% |
| 7 | Grok 4.6 | xhigh | 76.0% |
| 8 | MiMo V2.5 Pro | 75.3% | |
| 9 | Gemini 4 Carbon | high | 74.5% |
| 10 | Qwen 3.7 Max | max | 74.4% |
| 11 | Grok 4.3 | high | 74.2% |
| 12 | GLM 5.2 | max | 73.7% |
| 13 | GLM 5.3 Flash | max | 72.4% |
| 14 | Qwen 3.7 Plus | 72.3% | |
| 15 | Grok 4.7 | xhigh | 70.7% |
| 16 | GLM 5.3 | max | 70.4% |
| 17 | GLM 5.1 | 70.1% | |
| 18 | MiMo V2 Pro | 70.0% | |
| 19 | Qwen 3.8 27B | xhigh | 69.7% |
| 20 | Grok 4.6 | low | 69.4% |
| 21 | Muse Spark 1.3 | xhigh | 68.5% |
| 22 | Grok 4.7 | high | 67.6% |
| 23 | Muse Spark 1.3 | max | 67.1% |
| 24 | Muse Spark 1.2 | xhigh | 66.7% |
| 25 | GLM 5.2 | none | 66.3% |
| 26 | Grok 4.6 | high | 65.7% |
| 27 | Gemini 3.5 Flash-Lite | high | 65.6% |
| 28 | Qwen 3.6 Plus | 65.4% | |
| 29 | GLM 5 | 64.7% | |
| 30 | MiniMax M2.7 | 64.4% |