Benchmarks · reasoning
HLE-Diamond
HLE-Diamond: the refined 1,000-question version of Humanity's Last Exam from CAIS and Scale AI, split evenly between reasoning and knowledge questions; accuracy.
43 models · 94 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Carbon high
More from this benchmark
5 published measuresScore vs any published measure5 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| Gemini 4 Carbon high | 67,031,065 | 1,023,761 | 66,950,265 |
| Opus 5.5 max, fallback | 688,331 | 774,834 | 58,907,329 |
| GPT-6 Astra max | 646,278 | 198,139 | 10,696,945 |
| Fable 5.1 max, fallback | 684,444 | 591,397 | 55,120,583 |
| GPT-6.1 Sol max | 646,081 | 190,715 | 10,596,437 |
| Gemini 4 Argon high | 17,399,358 | 714,583 | 19,983,320 |
| Sonnet 5.5 max, fallback | 639,934 | 527,912 | 79,715,780 |
| GPT-6.1 Terra max | 647,158 | 143,487 | 29,027,705 |
| GPT-6 Sol max | 643,186 | 110,788 | 18,235,715 |
| Muse Spark 1.3 max | 562,962 | 238,146 | 37,188,219 |
| Gemini 3.8 Flash high | 568,339 | 453,520 | 25,699,399 |
| Haiku 5.5 max | 619,666 | 468,107 | 92,861,341 |
| GPT-5.6 Terra max | 646,471 | 159,152 | 31,510,329 |
| Kimi K3 max | 727,366 | 170,172 | 23,419,978 |
| DeepSeek V4.1 Flash 1017 max | 407,784 | 184,418 | 51,121,738 |
| Grok 4.7 high | 1,832,378 | 175,286 | 44,069,390 |
| GPT-6 Luna max | 642,597 | 140,713 | 29,520,279 |
| DeepSeek V4.1 Flash max | 407,039 | 128,867 | 33,686,774 |
| GLM 5.3 Flash max | 630,234 | 219,401 | 30,924,896 |
| GLM 5.3 max | 266,504 | 242,177 | 35,538,382 |
| MiniMax M3 | 712,166 | 405,279 | 23,051,265 |
| Qwen 3.8 27B xhigh | 547,972 | 534,518 | 33,925,438 |
| MiMo V2.6 Pro | 509,381 | 795,549 | 28,557,179 |
| Kimi K2.7 Code | 576,989 | 305,754 | 31,747,103 |
| Qwen 3.7 Plus | 522,824 | 402,720 | 31,703,847 |
All results
94 rows| # | Model | Effort | HLE-Diamond | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 69.1% | $1.63 | $1.63 |
| 2 | Opus 5.5 | max | 67.9% | $0.018 | $1.20 |
| 3 | Opus 5.5 | xhigh | 64.0% | $0.007 | $0.47 |
| 4 | GPT-6 Astra | max | 63.8% | $0.047 | $0.55 |
| 5 | GPT-6 Astra | xhigh | 61.5% | $0.032 | $0.37 |
| 6 | Fable 5.1 | max | 60.1% | $0.43 | $2.77 |
| 7 | GPT-6 Astra | high | 59.3% | $0.022 | $0.26 |
| 8 | Fable 5.1 | xhigh | 58.8% | $0.29 | $1.87 |
| 9 | GPT-6.1 Sol | max | 58.8% | $0.013 | $0.11 |
| 10 | Gemini 4 Argon | high | 56.7% | $0.17 | $0.48 |
| 11 | GPT-6.1 Sol | xhigh | 55.8% | $0.008 | $0.066 |
| 12 | Opus 5.5 | high | 55.6% | $0.003 | $0.19 |
| 13 | Sonnet 5.5 | max | 53.3% | $0.012 | $0.80 |
| 14 | GPT-6 Astra | medium | 52.7% | $0.010 | $0.12 |
| 15 | GPT-6.1 Sol | high | 51.9% | $0.005 | $0.043 |
| 16 | Opus 5.5 | medium | 51.4% | $0.002 | $0.13 |
| 17 | Fable 5.1 | high | 50.4% | $0.14 | $0.91 |
| 18 | GPT-6.1 Terra | max | 47.3% | $0.15 | $0.15 |
| 19 | GPT-6.1 Sol | medium | 46.0% | $0.002 | $0.019 |
| 20 | GPT-6 Sol | max | 45.2% | ||
| 21 | GPT-6 Astra | low | 45.1% | $0.004 | $0.050 |
| 22 | Fable 5.1 | medium | 45.0% | $0.071 | $0.46 |
| 23 | Sonnet 5.5 | xhigh | 44.1% | $0.004 | $0.25 |
| 24 | GPT-6.1 Terra | xhigh | 42.3% | $0.041 | $0.041 |
| 25 | Opus 5.5 | low | 41.7% | $0.001 | $0.035 |
| 26 | GPT-6.1 Sol | low | 38.2% | $0.001 | $0.009 |
| 27 | Fable 5.1 | low | 37.4% | $0.031 | $0.20 |
| 28 | GPT-6.1 Terra | high | 35.4% | $0.018 | $0.018 |
| 29 | Sonnet 5.5 | high | 33.8% | $0.002 | $0.11 |
| 30 | Muse Spark 1.3 | max | 33.7% | $0.080 | $0.16 |