| 模型 / 配置 | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.313 | 0.586 | 0.483 | — | 39.033 | 0.807 | 1,240.15 | 0.177 | 0.256 | 0.529 | 0.847 | — | — | — | — | — | — | — | |
| 0.525 | 0.593 | 0.547 | — | 39.767 | 0.843 | 1,592.56 | 0.277 | 0.256 | 0.612 | 0.857 | — | — | — | — | — | — | — | |
| 0.566 | 0.604 | 0.556 | — | 42.367 | 0.827 | 1,713.6 | 0.309 | 0.288 | 0.632 | 0.858 | — | — | — | — | — | — | — | |
| 0.596 | 0.65 | 0.575 | — | 43.133 | 0.847 | 1,835.03 | 0.317 | 0.266 | 0.65 | 0.866 | — | — | — | — | — | — | — | |
| 0.596 | 0.669 | 0.614 | — | 48.133 | 0.847 | 1,866.27 | 0.317 | 0.262 | 0.695 | 0.877 | — | — | — | — | — | — | — | |
| 0.419 | 0.541 | 0.492 | 0.931 | 40.3 | 0.8 | 1,403.26 | 0.263 | 0.304 | 0.591 | 0.846 | — | — | — | — | 0.32 | — | 0.88 | |
| 0.495 | 0.542 | 0.527 | 0.939 | 41.4 | 0.797 | 1,498.47 | 0.291 | 0.304 | 0.646 | 0.851 | — | — | — | — | 0.355 | — | 0.895 | |
| 0.54 | 0.554 | 0.531 | 0.949 | 44.567 | 0.8 | 1,536.04 | 0.289 | 0.31 | 0.666 | 0.864 | — | — | — | — | 0.4 | — | 0.899 | |
| 0.596 | 0.557 | 0.546 | 0.963 | 43.667 | 0.8 | 1,569.36 | 0.314 | 0.322 | 0.672 | 0.862 | — | — | — | — | 0.431 | — | 0.891 | |
| 0.591 | 0.565 | 0.547 | 0.961 | 42.433 | 0.807 | 1,583.69 | 0.317 | 0.31 | 0.685 | 0.869 | — | — | — | — | 0.414 | — | 0.884 | |
| 0.308 | 0.532 | 0.474 | — | 38 | 0.84 | 1,321.98 | 0.249 | 0.27 | 0.526 | 0.831 | — | — | — | — | — | — | — | |
| 0.48 | 0.532 | 0.499 | — | 40.167 | 0.833 | 1,459.05 | 0.277 | 0.3 | 0.626 | 0.839 | — | — | — | — | — | — | — | |
| 0.515 | 0.558 | 0.514 | — | 41 | 0.823 | 1,520.45 | 0.3 | 0.32 | 0.645 | 0.849 | — | — | — | — | — | — | — | |
| 0.54 | 0.557 | 0.526 | — | 42.367 | 0.797 | 1,554.8 | 0.317 | 0.318 | 0.666 | 0.851 | — | — | — | — | — | — | — | |
| 0.561 | 0.542 | 0.529 | — | 42.033 | 0.83 | 1,608.89 | 0.317 | 0.31 | 0.649 | 0.86 | — | — | — | — | — | — | — | |
| 0.152 | 0.524 | 0.358 | — | 22.933 | 0.81 | 1,203.75 | 0.151 | 0.256 | 0.562 | 0.825 | — | — | — | — | — | — | — | |
| 0.323 | 0.516 | 0.402 | — | 26.6 | 0.807 | 1,324.7 | 0.214 | 0.284 | 0.578 | 0.828 | — | — | — | — | — | — | — | |
| 0.419 | 0.516 | 0.433 | — | 27.767 | 0.823 | 1,352.74 | 0.257 | 0.28 | 0.585 | 0.838 | — | — | — | — | — | — | — | |
| 0.465 | 0.534 | 0.437 | — | 28.933 | 0.817 | 1,414.87 | 0.266 | 0.266 | 0.599 | 0.838 | — | — | — | — | — | — | — | |
| 0.556 | 0.551 | 0.462 | — | 29.567 | 0.827 | 1,475.63 | 0.28 | 0.286 | 0.602 | 0.847 | — | — | — | — | — | — | — | |
| 0.571 | 0.618 | 0.571 | — | 46.1 | 0.797 | 1,630.66 | 0.271 | 0.218 | 0.775 | — | — | — | — | — | — | — | — | |
| 0.571 | 0.626 | 0.536 | — | 30.6 | 0.837 | 1,857.09 | 0.329 | 0.326 | 0.713 | — | — | — | — | — | — | — | — | |
| 0.404 | 0.567 | 0.489 | 0.881 | 33.933 | 0.823 | 1,476.7 | 0.277 | 0.28 | 0.522 | — | — | — | — | — | 0.39 | — | 0.85 | |
| 0.449 | 0.564 | 0.538 | 0.886 | 36.433 | 0.847 | 1,554.23 | 0.291 | 0.268 | 0.547 | — | — | — | — | — | 0.41 | — | 0.88 | |
| 0.52 | 0.587 | 0.559 | 0.906 | 39.933 | 0.837 | 1,644.08 | 0.303 | 0.268 | 0.553 | — | — | — | — | — | 0.431 | — | 0.899 | |
| 0.551 | 0.609 | 0.587 | 0.934 | 44.333 | 0.83 | 1,740.22 | 0.311 | 0.262 | 0.578 | — | — | — | — | — | 0.458 | — | 0.91 | |
| 0.52 | 0.631 | 0.591 | 0.937 | 46.267 | 0.853 | 1,763.29 | 0.297 | 0.262 | 0.594 | — | — | — | — | — | 0.472 | — | 0.914 | |
| 0.52 | 0.603 | 0.501 | — | 25.1 | 0.807 | 1,770.34 | 0.283 | 0.306 | 0.681 | — | — | — | — | — | — | — | — | |
| 0.126 | 0.492 | 0.27 | — | 2.167 | 0.72 | 1,130.36 | 0.091 | 0.112 | 0.229 | — | — | — | — | — | — | — | — | |
| 0.152 | 0.49 | 0.338 | — | 4.167 | 0.773 | 1,282.5 | 0.129 | 0.152 | 0.286 | — | — | — | — | — | — | — | — | |
| 0.217 | 0.487 | 0.373 | — | 5.3 | 0.773 | 1,424.29 | 0.186 | 0.172 | 0.337 | — | — | — | — | — | — | — | — | |
| 0.293 | 0.517 | 0.427 | — | 7.833 | 0.783 | 1,521.54 | 0.226 | 0.182 | 0.36 | — | — | — | — | — | — | — | — | |
| 0.328 | 0.55 | 0.444 | — | 12.3 | 0.827 | 1,630.83 | 0.189 | 0.208 | 0.354 | — | — | — | — | — | — | — | — | |
| 0.162 | 0.549 | 0.392 | — | 27.4 | 0.8 | 1,591.4 | 0.134 | 0.214 | 0.567 | 0.782 | — | — | — | — | — | — | — | |
| 0.247 | 0.578 | 0.423 | — | 30 | 0.77 | 1,715.8 | 0.18 | 0.232 | 0.635 | — | — | — | — | — | — | — | — | |
| 0.258 | 0.574 | 0.431 | — | 31.233 | 0.767 | 1,718.42 | 0.177 | 0.2 | 0.656 | — | — | — | — | — | — | — | — | |
| 0 | 0.469 | 0.203 | — | -18.1 | 0.74 | 1,040.48 | 0.026 | 0.09 | 0.12 | 0.76 | — | — | — | — | — | — | — | |
| 0.025 | 0.509 | 0.283 | — | -13.567 | 0.783 | 1,270.45 | 0.106 | 0.138 | 0.405 | 0.779 | — | — | — | — | — | — | — | |
| 0.045 | 0.503 | 0.329 | — | -12.8 | 0.793 | 1,352.1 | 0.154 | 0.182 | 0.478 | 0.775 | — | — | — | — | — | — | — | |
| 0.081 | 0.517 | 0.343 | — | -12.967 | 0.8 | 1,372.52 | 0.174 | 0.186 | 0.478 | 0.797 | — | — | — | — | — | — | — | |
| 0.126 | 0.546 | 0.385 | — | -8.267 | 0.833 | 1,444.46 | 0.194 | 0.228 | 0.532 | 0.797 | — | — | — | — | — | — | — |
| 模型 / 配置 | ||||||
|---|---|---|---|---|---|---|
| 42.174 | 47.504 | 43.476 | 45.14 | 42.967 | 45.155 | |
| 50.745 | 55.988 | 49.71 | 51.42 | 53.599 | 54.329 | |
| 53.255 | 57.569 | 51.953 | 52.483 | 57.696 | 56.892 | |
| 55.72 | 59.002 | 54.723 | 55.514 | 62.472 | 60.004 | |
| 59.399 | 61.443 | 58.039 | 57.917 | 64.576 | 62.327 | |
| 48.121 | 49.879 | 47.688 | 44.982 | 49.524 | 47.826 | |
| 53.691 | 55.663 | 51.829 | 49.64 | 56.698 | 53.901 | |
| 56.134 | 57.196 | 55.062 | 51.565 | 59.977 | 56.645 | |
| 56.81 | 57.861 | 55.654 | 52.65 | 60.329 | 57.793 | |
| 57.378 | 57.975 | 55.569 | 53.731 | 61.795 | 58.322 | |
| 44.25 | 45.573 | 42.927 | 39.678 | 42.27 | 43.438 | |
| 50.602 | 53.259 | 49.002 | 45.817 | 51.853 | 50.267 | |
| 53.178 | 55.443 | 51.773 | 48.813 | 55.276 | 53.669 | |
| 55.209 | 57.238 | 53.682 | 50.756 | 57.301 | 55.716 | |
| 56.228 | 57.613 | 53.664 | 52.034 | 59.253 | 57.424 | |
| 37.943 | 42.176 | 37.256 | — | 35.016 | 35.996 | |
| 42.495 | 45.449 | 40.499 | — | 42.562 | 41.067 | |
| 44.208 | 47.449 | 42.5 | — | 46.325 | 43.627 | |
| 47.636 | 48.659 | 43.765 | — | 49.117 | 46.741 | |
| 48.994 | 50.015 | 46.384 | 44.723 | 54.386 | 49.323 | |
| 55.924 | 57.201 | 54.576 | 51.282 | 57.302 | 53.963 | |
| 55.228 | 57.898 | 50.725 | 51.886 | 54.921 | 55.565 | |
| 47.719 | 51.134 | 46.688 | 44.064 | 45.367 | 49.178 | |
| 47.469 | 52.305 | 48.082 | 45.311 | 50.048 | 50.997 | |
| 49.613 | 53.793 | 49.817 | 47.89 | 54.148 | 53.727 | |
| 53.509 | 56.435 | 53.731 | 50.537 | 56.884 | 57.944 | |
| 53.82 | 57.967 | 54.497 | 51.174 | 56.589 | 58.933 | |
| 51.13 | 54.482 | 46.869 | 48.703 | 49.303 | 50.886 | |
| 28.507 | 27.288 | 27.118 | 24.839 | 26.847 | 29.548 | |
| 34.877 | 32.973 | 32.604 | 30.698 | 31.795 | 35.55 | |
| 37.843 | 37.11 | 35.039 | 32.191 | 36.253 | 39.44 | |
| 41.107 | 39.138 | 37.147 | 34.113 | 40.26 | 42.633 | |
| 43.559 | 39.115 | 38.667 | 37.498 | 42.288 | 44.348 | |
| 45.299 | 49.258 | 44.402 | 42.897 | 37.437 | 42.752 | |
| 50.621 | 53.15 | 46.623 | 46.356 | 41.466 | 47.238 | |
| 51.689 | 54.827 | 47.196 | 46.599 | 40.951 | 47.584 | |
| 17.175 | 16.801 | 16.348 | 16.168 | 18.727 | 18.722 | |
| 26.285 | 33.758 | 24.459 | 27.404 | 24.777 | 27.503 | |
| 29.26 | 37.788 | 26.663 | 29.248 | 27.207 | 29.847 | |
| 30.551 | 39.393 | 28.382 | 30.489 | 28.839 | 32.105 | |
| 33.868 | 43.188 | 32.211 | 34.824 | 33.199 | 35.485 |
| 模型 / 配置 | 智能 | 每项任务输出 Token | 输出 Token 总量 | 每项任务成本 (USD) | 评测总成本 (USD) | 每项任务耗时 (s) |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 (Low, Default Fallback) | 38.4836488107 | 37,836.5127212 | 36,344,445 | 4.47113589465 | 3,885.93502864 | 413.730600196 |
| GPT-6.1 Sol (Xhigh) | 52.3082192533 | 30,241.1839475 | 33,286,283 | 0.763994935616 | 717.708156949 | 425.698330478 |
| GPT-6 Luna (Xhigh) | 23.3008728089 | 43,893.2141033 | 56,118,451 | 0.104093209211 | 85.744011654 | 362.243332216 |
| GPT-6 Astra (Xhigh) | 55.255746857 | 26,723.7585954 | 32,284,672 | 3.65892649061 | 3,746.21535857 | 406.085509866 |
| Claude Haiku 5.5 (High) | 29.6243154677 | 88,064.3478049 | 89,814,062 | 0.158560319567 | 121.413039537 | 305.719268626 |
| Grok 4.7 (Low) | 30.8820776026 | 42,669.5849076 | 51,253,468 | 2.92220130119 | 2,168.64512758 | 588.121973091 |
| Grok 4.7 (High) | 35.012296296 | 89,127.175774 | 123,196,074 | 6.18359556538 | 4,721.60742497 | 1,113.10958533 |
| GPT-6 Astra (Max) | 56.8538559597 | 51,973.1989764 | 54,327,859 | 6.2446669436 | 5,661.17948256 | 658.382490935 |
| Claude Opus 5.5 (Max, Default Fallback) | 58.4060336079 | 173,312.638857 | 218,145,408 | 10.0364097195 | 8,909.66701565 | 1,140.77864281 |
| GPT-6 Luna (Medium) | 18.3042156192 | 19,823.23818 | 24,887,351 | 0.0422018361065 | 39.5503276316 | — |
| Claude Fable 5.1 (Medium, Default Fallback) | 42.9715978283 | 48,545.4956524 | 49,158,531 | 5.56426469022 | 4,896.57665942 | 536.274658397 |
| GPT-6.1 Sol (High) | 50.2291231937 | 22,606.1990718 | 24,651,130 | 0.590985351578 | 573.167791013 | 374.606289867 |
| Claude Fable 5.1 (Max, Default Fallback) | 49.0102124158 | 117,940.937972 | 163,073,497 | 12.9939972012 | 13,326.7785223 | 1,073.88598588 |
| Claude Haiku 5.5 (Xhigh) | 34.3387759487 | 136,176.990729 | 150,911,615 | 0.248361101266 | 192.695109987 | 466.539286921 |
| Claude Haiku 5.5 (Low) | 18.6180055311 | 28,160.5500092 | 29,899,488 | 0.043757686382 | 39.6028900779 | 115.218049314 |
| Claude Opus 5.5 (Low, Default Fallback) | 34.5027850078 | 19,059.5574657 | 21,114,634 | 0.975529322446 | 979.656483804 | 153.000427601 |
| Grok 4.7 (Xhigh) | 34.3350117067 | 92,969.506435 | 142,604,745 | 7.51176958641 | 5,784.2724639 | 1,089.75456883 |
| GPT-6 Luna (Max) | 27.7552004938 | 75,296.0523656 | 109,588,316 | 0.151955757321 | 136.060821851 | 631.021642241 |
| Claude Haiku 5.5 (Max) | 36.234543588 | 225,965.959716 | 297,721,915 | 0.411007415368 | 339.472802241 | 592.373239664 |
| GPT-6 Luna (High) | 21.3790170865 | 32,839.1412292 | 40,451,607 | 0.0729477647319 | 62.5750472458 | 287.856450326 |
| Claude Fable 5.1 (Xhigh, Default Fallback) | 49.6716384249 | 97,058.7880449 | 114,929,206 | 10.8474747061 | 10,096.622785 | 970.62018404 |
| Claude Fable 5.1 (High, Default Fallback) | 47.0249882456 | 66,030.7134672 | 69,641,442 | 7.53995616023 | 6,617.89007374 | 733.231047376 |
| GPT-6.1 Sol (Medium) | 46.1468797067 | 13,518.3359352 | 15,120,833 | 0.359389864803 | 388.568776851 | 264.321113566 |
| GPT-6 Astra (Low) | 43.0349823229 | 9,125.80899961 | 10,270,307 | 1.42372296357 | 1,650.74841495 | 156.962743118 |
| Claude Haiku 5.5 (Medium) | 24.5513254343 | 53,335.1165198 | 52,730,406 | 0.0917645584067 | 72.6994579627 | 195.301464617 |
| GPT-6.1 Terra (Max) | 50.9765188577 | 59,883.1647179 | 99,386,052 | 0.961108031082 | 972.335839003 | 610.145274863 |
| GPT-6.1 Sol (Max) | 54.5087338138 | 67,823.6917378 | 63,661,006 | 1.27206326794 | 1,123.97392095 | 927.671787286 |
| GPT-6 Luna (Low) | 9.66610812336 | 3,295.89033539 | 5,823,065 | 0.00511525518852 | 9.08719279335 | 26.2601585366 |
| GPT-6.1 Terra (Medium) | 38.1152076678 | 10,875.4627408 | 13,627,217 | 0.168804582384 | 190.360237377 | 118.859280809 |
| GPT-6.1 Terra (Low) | 29.2169280792 | 4,422.17226751 | 7,189,028 | 0.0713375620517 | 111.160604312 | 48.2504205658 |
| Gemini 4 Argon (High) | 50.4121935905 | 116,368.029068 | 113,329,224 | 7.68267137252 | 6,102.83700363 | 1,363.84651098 |
| Claude Opus 5.5 (Xhigh, Default Fallback) | 56.9947060171 | 103,395.266992 | 100,823,907 | 6.04719449085 | 4,765.90876597 | 792.738520875 |
| GPT-6 Astra (High) | 54.8498383225 | 23,133.4696365 | 25,584,856 | 3.23857196855 | 3,203.9990981 | 356.028422567 |
| GPT-6.1 Sol (Low) | 34.5029244315 | 5,837.99467626 | 8,177,481 | 0.161473578318 | 237.907998542 | 112.769004749 |
| GPT-6.1 Terra (Xhigh) | 44.9500517891 | 26,199.6591832 | 34,722,763 | 0.400689001667 | 400.175781606 | 283.216645159 |
| GPT-6 Astra (Medium) | 51.4548393864 | 18,051.6244271 | 18,172,704 | 2.73243893301 | 2,638.28926372 | 318.188702459 |
| Muse Wonder Full (Max) | 49.7272123627 | 88,475.6149841 | 111,539,103 | — | — | — |
| GPT-6.1 Terra (High) | 42.3344508713 | 16,746.4773224 | 20,580,034 | 0.259279646617 | 266.794983365 | 180.100229908 |
| Claude Opus 5.5 (Medium, Default Fallback) | 48.0581024961 | 43,816.5464788 | 42,531,163 | 2.45108943766 | 2,031.26960729 | 346.911299325 |
| Claude Opus 5.5 (High, Default Fallback) | 51.6859958227 | 60,070.9585554 | 56,144,369 | 3.4646622821 | 2,715.98000128 | 473.897676499 |
| Muse Wonder (Max) | 43.3248225998 | 96,063.0990918 | 113,389,708 | 6.95203647861 | 5,414.45363704 | 682.093132618 |
按发布日期比较模型分数。
显示 86 项,共 86 项
帕累托前沿| 排名 | 模型 | 得分 | 已发布 | 来源 |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (最高)Anthropic | 58.4 | 2026年9月22日 | |
| 2 | Claude Opus 5.5 (极高)Anthropic | 57 | 2026年9月22日 | |
| 3 | GPT-6 Astra (最高)OpenAI | 56.9 | 2026年9月03日 | |
| 4 | GPT-6 Astra (极高)OpenAI | 55.3 | 2026年9月03日 | |
| 5 | GPT-6 Astra (高)OpenAI | 54.8 | 2026年9月03日 | |
| 6 | GPT-6.1 Sol (最高)OpenAI | 54.5 | 2026年9月29日 | |
| 7 | Claude Sonnet 5.5 (最高)Anthropic | 54.2 | 2026年9月28日 | |
| 8 | GPT-6.1 Sol (极高)OpenAI | 52.3 | 2026年9月29日 | |
| 9 | Claude Opus 5.5 (高)Anthropic | 51.7 | 2026年9月22日 | |
| 10 | GPT-6 Astra (中)OpenAI | 51.5 | 2026年9月03日 | |
| 11 | GPT-6.1 Terra (最高)OpenAI | 51 | 2026年10月26日 | |
| 12 | Gemini 4 Argon (高)Google | 50.4 | 2026年10月13日 | |
| 13 | GPT-6.1 Sol (高)OpenAI | 50.2 | 2026年9月29日 | |
| 14 | Claude Fable 5.1 (极高)Anthropic | 49.7 | 2026年9月01日 | |
| 14 | 49.7 | 2026年10月12日 | ||
| 16 | Claude Sonnet 5.5 (极高)Anthropic | 49.6 | 2026年9月28日 | |
| 17 | Claude Fable 5.1 (最高)Anthropic | 49 | 2026年9月01日 | |
| 18 | Claude Opus 5.5 (中)Anthropic | 48.1 | 2026年9月22日 | |
| 19 | Claude Fable 5.1 (高)Anthropic | 47 | 2026年9月01日 | |
| 20 | GPT-6.1 Sol (中)OpenAI | 46.1 | 2026年9月29日 | |
| 21 | Kimi K3.1 Pro (默认)Moonshot | 46 | 2026年10月23日 | |
| 22 | GPT-6.1 Terra (极高)OpenAI | 45 | 2026年10月26日 | |
| 23 | 43.3 | 2026年10月12日 | ||
| 24 | GPT-6 Astra (低)OpenAI | 43 | 2026年9月03日 | |
| 24 | Claude Fable 5.1 (中)Anthropic | 43 | 2026年9月01日 |