HyperAI
Command Palette
Search for a command to run...
HLE-Diamond
Humanity's Last Examの洗練・更新された1,000問のセット。推論問題と知識問題が均等に分かれ、272問が画像を含む。
- カテゴリ
- 一般
- インテリジェンス指標の重み
- 10%
- モデル
- 133 現在、 162 合計
- 中央値
- 17.3%
- 範囲
- 2.8%–80.2%
| ランク | 比較する | モデル | スコア | コスト / タスク | 時間 / タスク | 出力 token / タスク |
|---|---|---|---|---|---|---|
| 51 | 23.8% | $0.033 | 22.5s | 3.13K | ||
| 52 |  Claude Haiku 5.5 (High) Anthropic | 23.7% | $0.011 | 1m 36s | 22K | |
| 53 |  Grok 4.7 (High) SpaceXAI | 23.6% | $0.27 | 10m 57s | 44.2K | |
| 54 | 23.6% | $0.017 | 1m 14s | 33.7K | ||
| 55 | Grok 4.7 (Xhigh) SpaceXAI | 23.2% | $0.33 | 14m 9s | 54.3K | |
| 56 |  GPT-6 Luna (Max) OpenAI | 22.2% | $0.015 | 4m 31s | 29.7K | |
| 57 |  DeepSeek V4 Flash Vision (Max) DeepSeek | 21.1% | — | — | — | |
| 58 | DeepSeek V4.1 Flash 1017 (High) DeepSeek | 20.8% | $0.036 | 3m 32s | 30K | |
| 59 | 20.6% | $0.015 | 9.8s | 1.36K | ||
| 60 |  Qwen3.8 2.4T A95B Alibaba | 20.1% | — | — | — | |
| 61 | DeepSeek V4 Pro 0813 (Max) DeepSeek | 19.5% | $0.12 | 7m 22s | 30.6K | |
| 62 | GPT-6 Luna (Xhigh) OpenAI | 18.9% | $0.0062 | 1m 59s | 12.3K | |
| 63 | Grok 4.7 (Low) SpaceXAI | 18.5% | $0.099 | 4m 6s | 15.9K | |
| 64 |  GLM-5.3-Flash Z AI | 18.2% | $0.016 | 10m 29s | 31.1K | |
| 65 | GLM-5.3 (Max) Z AI | 17.9% | $0.16 | 8m 41s | 35.8K | |
| 66 | GLM-5.3 (Low) Z AI | 17.5% | $0.12 | 7m 58s | 28.2K | |
| 67 |  Mistral Large 4 (High) Mistral | 17.3% | $0.081 | 5m 27s | 38.3K | |
| 68 |  Ling 3.1 Flash 1019 InclusionAI | 17.2% | $0.043 | — | 47.8K | |
| 69 |  Agnes 2.5 Pro Theta Sapiens AI | 16.8% | $0.017 | 4m 50s | 56K | |
| 70 | Claude Haiku 5.5 (Medium) Anthropic | 16.8% | $0.0043 | 37.6s | 8.46K | |
| 71 | Qwen3.8-Flash-Next Alibaba | 16.3% | — | — | — | |
| 72 |  MiniMax-M3 MiniMax | 16.0% | $0.028 | 3m 9s | 23.5K | |
| 73 | GPT-6 Luna (High) OpenAI | 15.6% | $0.0036 | 1m 13s | 7.12K | |
| 74 | Qwen3.8 27B (Xhigh) Alibaba | 15.3% | $0.10 | 12m 27s | 34.5K | |
| 75 |  MiMo-V2.6-Pro Xiaomi | 15.2% | $0.026 | 8m 40s | 29.4K | |
| 76 | GPT-6 Luna (Medium) OpenAI | 15.1% | $0.0017 | 33.3s | 3.32K | |
| 77 |  Kimi K2.7 Code Kimi | 14.8% | — | — | — | |
| 78 | 14.6% | — | — | — | ||
| 79 | 14.5% | $0.0011 | 1.3s | 92.3 | ||
| 80 | Claude Haiku 5.5 (Low) Anthropic | 14.1% | $0.0017 | 15.1s | 3.31K | |
| 81 | Mistral Large 4 (Medium) Mistral | 13.9% | $0.06 | 4m 13s | 28.6K | |
| 82 | Qwen3.7 Plus Alibaba | 13.9% | — | — | — | |
| 83 | MiMo-V2.6-Flash Xiaomi | 13.7% | $0.011 | 18m 11s | 38.3K | |
| 84 |  Quasar 438B (Max, Based on GLM-5.2) Multiverse Computing | 13.1% | — | — | — | |
| 85 |  Beam 1.0 Reflection | 12.8% | $0.018 | 53.0s | 15.3K | |
| 86 | 12.4% | — | — | — | ||
| 87 |  Inkling Small Thinking Machines | 12.1% | $0.04 | 7m 48s | 33.5K | |
| 88 |  Apodex 1.1 Apodex | 11.6% | $0.14 | 5m 27s | 46.5K | |
| 89 |  Hy3 Tencent | 11.6% | — | — | — | |
| 90 |  LongCat 2.0 LongCat | 11.5% | — | — | — | |
| 91 | Inkling (Xhigh) Thinking Machines | 10.6% | $0.13 | 5m 36s | 32.7K | |
| 92 | GPT-6 Luna (Low) OpenAI | 10.2% | $0.00053 | 10.7s | 929 | |
| 93 |  K2 Horizon 375B A23B Institute of Foundation Models | 10.2% | $0 | 2m 30s | 28.3K | |
| 94 |  Gemini 3.5 Flash-Lite Google | 9.9% | $0.02 | 25.4s | 7.89K | |
| 95 | 9.1% | $0.0091 | 1m 23s | 7.47K | ||
| 96 |  Nemotron 3.5 Super VL NVIDIA | 8.8% | $0.021 | 2m 44s | 42.5K | |
| 97 | 8.5% | $0.069 | 2m 15s | 25.6K | ||
| 98 | Ling-3.0-flash-VL InclusionAI | 7.6% | — | — | — | |
| 99 | 7.3% | — | — | — | ||
| 100 | 7.2% | $0.0045 | 15.8s | 1.05K |
- 52