AA HLE-Diamond - Knowledge: leaderboard
Artificial Analysis accuracy on HLE-Diamond’s 500-question knowledge partition. One answer without tools, official HLE prompts and GPT-5.6 Luna (medium) judge; image-capable models receive images and other models receive the question text. Scores are percentages.
Metric: Accuracy (%). Source: artificialanalysis.ai. Saturation forecast: Around September 2028. 133 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Carbon (High) | 58.6 | #2 (Gemini 4 Carbon) |
| 2 | GPT-6 Astra (Max) | 49.6 | #5 (GPT-6 Astra) |
| 3 | Gemini 4 Argon (High) | 48.6 | #9 (Gemini 4 Argon) |
| 4 | GPT-6 Astra (xHigh) | 48 | #5 (GPT-6 Astra) |
| 5 | GPT-6 Astra (High) | 46.8 | #5 (GPT-6 Astra) |
| 6 | GPT-6.1 Sol (xHigh) | 43.6 | #7 (GPT-6.1 Sol) |
| 7 | GPT-6.1 Sol (Max) | 41.4 | #7 (GPT-6.1 Sol) |
| 8 | GPT-6 Astra (Medium) | 41.2 | #5 (GPT-6 Astra) |
| 9 | GPT-6.1 Sol (High) | 40.2 | #7 (GPT-6.1 Sol) |
| 10 | GPT-6 Astra (Low) | 36 | #5 (GPT-6 Astra) |
| 11 | GPT-6.1 Sol (Medium) | 35.8 | #7 (GPT-6.1 Sol) |
| 12 | Muse Wonder Full (Max) | 35.8 | #11 (Muse Wonder Full) |
| 13 | GPT-6.1 Sol (Low) | 31.6 | #7 (GPT-6.1 Sol) |
| 14 | GPT-6 Sol (Max) | 30.8 | #18 (GPT-6 Sol) |
| 15 | Kimi K3.1 Pro | 29.8 | #16 |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-hle-diamond-knowledge · How It Works · Data refreshed daily, snapshot 2026-10-29.