HyperAI
Command Palette
Search for a command to run...
HLE-Diamond
Humanity's Last Exam의 1,000문항으로 정제하고 갱신한 세트로, 추론과 지식 문항이 균등하게 나뉘며 272개 문항에는 이미지가 포함됩니다.
- 카테고리
- 일반
- 지능 지수 가중치
- 10%
- 모델
- 133 현재, 162 전체
- 중앙값
- 17.3%
- 범위
- 2.8%–80.2%
| 순위 | 비교 | 모델 | 점수 | 비용 / 작업 | 시간 / 작업 | 출력 토큰 / 작업 |
|---|---|---|---|---|---|---|
| 101 | Gemma 4 31B (Reasoning) Google | 7.2% | — | — | — | |
| 102 | 7.1% | $0.0013 | 8.1s | 1.01K | ||
| 103 | Nanbeige4.3-33B Nanbeige | 6.9% | — | — | 27.1K | |
| 104 | Qwen3.6 35B A3B (Reasoning) Alibaba | 6.9% | — | — | — | |
| 105 | Qwen3.8 27B (Low) Alibaba | 6.8% | $0.016 | 1m 42s | 5.12K | |
| 106 | Qwen3.8 27B (Medium) Alibaba | 6.7% | $0.025 | 3m 2s | 8.13K | |
| 107 | 6.3% | $0.00013 | 1.5s | 138 | ||
| 108 | 6.2% | — | — | — | ||
| 109 | Trinity Large Thinking Arcee AI | 6.0% | — | — | — | |
| 110 | Celeris-1 Celeris | 5.7% | — | — | — | |
| 111 | K-EXAONE 2.0 LG AI Research | 5.7% | — | — | 17.8K | |
| 112 | Ling-3.0-flash-Fin InclusionAI | 5.4% | — | — | — | |
| 113 | Command A+ Cohere | 5.1% | $0 | 1m 55s | 22.9K | |
| 114 | Mercury 2.5 Inception | 5.1% | — | — | — | |
| 115 | Ministral 3 3B Mistral | 5.1% | — | — | — | |
| 116 | gpt-oss-20b (High) OpenAI | 4.8% | — | — | — | |
| 117 | Qwen3.5 9B (Reasoning) Alibaba | 4.8% | — | — | — | |
| 118 | Mistral Medium 3.5 Mistral | 4.7% | $0.14 | 2m 10s | 18.2K | |
| 119 | Solar Pro 4 Upstage | 4.7% | — | — | — | |
| 120 | Nemotron 3.5 Lightning NVIDIA | 4.5% | $0.0035 | 1m 12s | 17.6K | |
| 121 | Ministral 3 14B Mistral | 4.4% | — | — | — | |
| 122 | Ministral 3 8B Mistral | 4.4% | — | — | — | |
| 123 | Mistral Small 4 (Reasoning) Mistral | 4.4% | $0.0064 | 1m 12s | 10.5K | |
| 124 | 4.3% | — | — | — | ||
| 125 | Qwen3 Coder Next Alibaba | 4.3% | — | — | — | |
| 126 | North Mini Code Cohere | 4.2% | $0 | 1m 41s | 17.1K | |
| 127 | Qwen3.8 27B (Non-reasoning) Alibaba | 4.2% | $0.01 | 1m 24s | 3.41K | |
| 128 | 4.0% | $0.0033 | 2m 17s | 13.2K | ||
| 129 | gpt-oss-120b (High) OpenAI | 3.8% | $0.0049 | 50.5s | 8.16K | |
| 130 | MiniCPM5-2B OpenBMB | 3.8% | — | — | — | |
| 131 | 3.5% | — | — | — | ||
| 132 | 2.9% | — | — | 12.5K | ||
| 133 | 2.8% | — | — | 1.39K |