HyperAI
Command Palette
Search for a command to run...
Humanity's Last Exam
수학, 과학, 인문학에 걸친 전문가 검증 2,500문항으로 구성된 프런티어 수준 벤치마크로, 최종적인 폐쇄형 학술 평가를 목표로 설계되었습니다.
- 모델
- 267 현재, 684 전체
- 중앙값
- 12.0%
- 범위
- 1.1%–74.3%
| 순위 | 비교 | 모델 | 점수 |
|---|---|---|---|
| 51 |  GPT-6.1 Terra (Medium) OpenAI | 40.2% | |
| 52 |  GLM-5.3-Flash Z AI | 39.9% | |
| 53 | 39.8% | ||
| 54 |  Ling 3.1 Flash InclusionAI | 39.4% | |
| 55 |  Grok 4.7 (Low) SpaceXAI | 39.2% | |
| 56 |  MiniMax-M3 MiniMax | 39.0% | |
| 57 | GPT-6 Luna (Max) OpenAI | 38.5% | |
| 58 |  Qwen3.8-Flash-Next Alibaba | 38.0% | |
| 59 |  Agnes 2.5 Pro Beta Sapiens AI | 37.5% | |
| 60 |  Claude Haiku 5.5 (High) Anthropic | 37.3% | |
| 61 | Agnes 2.5 Pro Theta Sapiens AI | 37.2% | |
| 62 |  Gemini 3.8 Flash (Low) Google | 37.1% | |
| 63 |  Motif 3 Motif Technologies | 37.0% | |
| 64 | GLM-5.3 (Low) Z AI | 36.6% | |
| 65 | 36.2% | ||
| 66 | GPT-6.1 Terra (Low) OpenAI | 35.8% | |
| 67 | Qwen3.7 Plus Alibaba | 35.6% | |
| 68 |  MiMo-V2.6-Flash Xiaomi | 35.1% | |
| 69 |  Kimi K2.7 Code Kimi | 35.0% | |
| 70 |  Beam 1.0 Reflection | 34.7% | |
| 71 |  DeepSeek V4 Flash Vision (Max) DeepSeek | 34.5% | |
| 72 | GPT-6 Luna (Xhigh) OpenAI | 34.3% | |
| 73 |  Apodex 1.1 Apodex | 34.1% | |
| 74 | Qwen3.8 27B (Xhigh) Alibaba | 33.9% | |
| 75 | Claude Haiku 5.5 (Medium) Anthropic | 33.8% | |
| 76 | 33.7% | ||
| 77 |  LongCat 2.0 LongCat | 33.7% | |
| 78 |  Hy3 Tencent | 33.5% | |
| 79 |  Inkling Small Thinking Machines | 33.3% | |
| 80 | GPT-6 Luna (High) OpenAI | 32.9% | |
| 81 |  K2 Horizon 375B A23B Institute of Foundation Models | 32.0% | |
| 82 | Inkling (Xhigh) Thinking Machines | 31.9% | |
| 83 |  Nemotron 3.5 Super VL NVIDIA | 30.7% | |
| 84 |  Solar Pro 4 Upstage | 29.8% | |
| 85 |  A.X-K2 SK Telecom | 29.6% | |
| 86 | 29.0% | ||
| 87 | Solar Open2 250B Upstage | 28.5% | |
| 88 | 28.4% | ||
| 89 | GPT-6 Luna (Medium) OpenAI | 28.3% | |
| 90 | Claude Haiku 5.5 (Low) Anthropic | 27.0% | |
| 91 | Solar Mini 4 Upstage | 25.8% | |
| 92 | 25.2% | ||
| 93 | 24.7% | ||
| 94 | Gemma 4 31B (Reasoning) Google | 23.6% | |
| 95 | K2 Horizon MoVA 36B A4B Institute of Foundation Models | 23.4% | |
| 96 | Ling-3.0-flash-Fin InclusionAI | 22.6% | |
| 97 | Qwen3.6 35B A3B (Reasoning) Alibaba | 22.2% | |
| 98 | Ling-3.0-flash-VL InclusionAI | 22.0% | |
| 99 | 22.0% | ||
| 100 | Ring-2.6-1T InclusionAI | 21.6% |
