Help keep public data accurate
See something missing, incorrect, or out of date? Tell us about this page.
See something missing, incorrect, or out of date? Tell us about this page.
AI benchmark results and model performance
Individual benchmark scores plotted by date.
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Gemini 4 Carbon | 10 Nov 2026 | 69.10% | Gemini 4 Carbon (High); Artificial Analysis ID 909ed0ba-bcc5-4f38-8162-08a4e187a772; HLE-Diamond | No | Source | |
| Gemini 4 Hydrogen | 12 Nov 2026 | 58.80% | Google-reported model card evaluation (Nov 2026); Claude Sonnet 5.5 53.3, GPT-6.1 Terra 47.3; methodology: deepmind.google/models/evals-methodology/gemini-4-hydrogen | Yes | Source | |
| Gemini 4 Argon | 13 Oct 2026 | 56.70% | Gemini 4 Argon (High); Artificial Analysis ID d366dfa1-d940-4788-aa73-d298c45699b3; HLE-Diamond | No | Source |
