AA HLE-Diamond: leaderboard
Artificial Analysis evaluates all 1,000 HLE-Diamond questions without tools: 500 reasoning and 500 knowledge, including 272 image questions. Each question receives one answer, graded with the official HLE prompts by GPT-5.6 Luna (medium). Text-only models receive the text of image questions and are still graded on all 1,000. Accuracy is a percentage.
Metric: Accuracy (%). Source: artificialanalysis.ai. Saturation forecast: Around February 2028. 133 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Carbon (High) | 69.1 | #2 (Gemini 4 Carbon) |
| 2 | GPT-6 Astra (Max) | 63.8 | #5 (GPT-6 Astra) |
| 3 | GPT-6 Astra (xHigh) | 61.5 | #5 (GPT-6 Astra) |
| 4 | GPT-6 Astra (High) | 59.3 | #5 (GPT-6 Astra) |
| 5 | GPT-6.1 Sol (Max) | 58.8 | #7 (GPT-6.1 Sol) |
| 6 | Gemini 4 Argon (High) | 56.7 | #9 (Gemini 4 Argon) |
| 7 | GPT-6.1 Sol (xHigh) | 55.8 | #7 (GPT-6.1 Sol) |
| 8 | GPT-6 Astra (Medium) | 52.7 | #5 (GPT-6 Astra) |
| 9 | GPT-6.1 Sol (High) | 51.9 | #7 (GPT-6.1 Sol) |
| 10 | Muse Wonder Full (Max) | 48.5 | #11 (Muse Wonder Full) |
| 11 | GPT-6.1 Terra (Max) | 47.3 | #13 (GPT-6.1 Terra) |
| 12 | GPT-6.1 Sol (Medium) | 46 | #7 (GPT-6.1 Sol) |
| 13 | GPT-6 Sol (Max) | 45.2 | #18 (GPT-6 Sol) |
| 14 | GPT-6 Astra (Low) | 45.1 | #5 (GPT-6 Astra) |
| 15 | GPT-6.1 Terra (xHigh) | 42.3 | #13 (GPT-6.1 Terra) |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-hle-diamond · How It Works · Data refreshed daily, snapshot 2026-10-29.