Model name | Ja avg | JComQA | JEMHQA | NIILC | JSQuAD | XL-Sum | MGSM | En-Ja | Ja-En | JMMLU | JHumanEval | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Falcon3-1B-Base | 0.129 | 0.216 | 0.251 | 0.062 | 0.281 | 0.085 | 0.008 | 0.012 | 0.020 | 0.264 | 0.088 | |
Falcon3-3B-Base | 0.209 | 0.281 | 0.333 | 0.113 | 0.517 | 0.120 | 0.096 | 0.031 | 0.051 | 0.319 | 0.229 | |
Falcon3-7B-Base | 0.337 | 0.634 | 0.412 | 0.180 | 0.788 | 0.173 | 0.244 | 0.078 | 0.119 | 0.385 | 0.361 | |
Falcon3-10B-Base | 0.383 | 0.680 | 0.443 | 0.187 | 0.854 | 0.187 | 0.376 | 0.103 | 0.139 | 0.435 | 0.426 | |
Gemma 2 2B | 0.348 | 0.721 | 0.472 | 0.316 | 0.810 | 0.083 | 0.124 | 0.203 | 0.190 | 0.388 | 0.177 | |
Gemma 2 9B | 0.500 | 0.904 | 0.573 | 0.524 | 0.898 | 0.168 | 0.456 | 0.269 | 0.236 | 0.623 | 0.345 | |
Gemma 2 27B | 0.546 | 0.936 | 0.553 | 0.573 | 0.916 | 0.194 | 0.596 | 0.295 | 0.251 | 0.659 | 0.490 | |
Gemma 2 Baku 2B | 0.372 | 0.760 | 0.475 | 0.443 | 0.843 | 0.121 | 0.124 | 0.255 | 0.187 | 0.376 | 0.137 | |
Llama 3 8B | 0.429 | 0.835 | 0.436 | 0.410 | 0.892 | 0.177 | 0.312 | 0.221 | 0.206 | 0.455 | 0.344 | |
Llama 3 70B | 0.569 | 0.946 | 0.606 | 0.589 | 0.922 | 0.228 | 0.664 | 0.286 | 0.252 | 0.705 | 0.491 | |
Llama 3 Swallow 8B | 0.471 | 0.896 | 0.478 | 0.546 | 0.900 | 0.198 | 0.440 | 0.276 | 0.222 | 0.471 | 0.282 | |
Llama 3 Swallow 70B | 0.594 | 0.968 | 0.675 | 0.684 | 0.923 | 0.239 | 0.708 | 0.307 | 0.255 | 0.706 | 0.477 | |
Llama 3 Youko 8B | 0.442 | 0.870 | 0.493 | 0.513 | 0.895 | 0.213 | 0.276 | 0.276 | 0.219 | 0.449 | 0.222 | |
Llama 3 Youko 70B | 0.571 | 0.946 | 0.602 | 0.610 | 0.923 | 0.242 | 0.684 | 0.292 | 0.250 | 0.704 | 0.463 | |
Llama 3.1 8B | 0.437 | 0.845 | 0.461 | 0.405 | 0.895 | 0.179 | 0.356 | 0.221 | 0.210 | 0.479 | 0.320 | |
Llama 3.1 70B | 0.566 | 0.946 | 0.616 | 0.603 | 0.925 | 0.228 | 0.672 | 0.287 | 0.257 | 0.669 | 0.462 | |
Llama 3.1 Swallow 8B v0.1 | 0.490 | 0.912 | 0.509 | 0.601 | 0.899 | 0.202 | 0.460 | 0.291 | 0.231 | 0.518 | 0.276 | |
Llama 3.1 Swallow 70B v0.1 | 0.593 | 0.955 | 0.645 | 0.678 | 0.923 | 0.272 | 0.684 | 0.320 | 0.259 | 0.709 | 0.487 | |
Llama 3.1 Swallow 8B v0.2 | 0.499 | 0.911 | 0.510 | 0.627 | 0.892 | 0.198 | 0.464 | 0.296 | 0.233 | 0.525 | 0.336 | |
Llama 3.2 1B | 0.201 | 0.208 | 0.404 | 0.188 | 0.525 | 0.081 | 0.024 | 0.079 | 0.092 | 0.260 | 0.150 | |
Llama 3.2 3B | 0.337 | 0.605 | 0.443 | 0.324 | 0.816 | 0.129 | 0.136 | 0.161 | 0.167 | 0.352 | 0.235 | |
Llama 3.3 Swallow 70B v0.4 | 0.629 | 0.967 | 0.671 | 0.732 | 0.924 | 0.283 | 0.776 | 0.327 | 0.260 | 0.742 | 0.604 | |
llm-jp-3-1.8b | 0.251 | 0.209 | 0.463 | 0.449 | 0.703 | 0.100 | 0.012 | 0.198 | 0.134 | 0.242 | 0.001 | |
llm-jp-3-3.7b | 0.281 | 0.203 | 0.431 | 0.541 | 0.804 | 0.142 | 0.060 | 0.223 | 0.159 | 0.249 | 0.000 | |
llm-jp-3-13b | 0.393 | 0.650 | 0.525 | 0.649 | 0.882 | 0.164 | 0.160 | 0.273 | 0.210 | 0.399 | 0.023 | |
Mistral-Nemo-Base-2407 (12B) | 0.460 | 0.911 | 0.516 | 0.475 | 0.904 | 0.192 | 0.416 | 0.244 | 0.212 | 0.538 | 0.194 | |
Mistral-NeMo-Minitron 8B | 0.444 | 0.887 | 0.486 | 0.374 | 0.902 | 0.157 | 0.424 | 0.186 | 0.193 | 0.494 | 0.332 | |
Mistral-7B-v0.3 | 0.361 | 0.714 | 0.474 | 0.245 | 0.847 | 0.212 | 0.156 | 0.142 | 0.171 | 0.404 | 0.242 | |
Mixtral-8x22B-v0.1 | 0.496 | 0.895 | 0.512 | 0.420 | 0.914 | 0.241 | 0.544 | 0.229 | 0.229 | 0.604 | 0.371 | |
PLaMo 2 1B | 0.250 | 0.203 | 0.463 | 0.434 | 0.626 | 0.055 | 0.052 | 0.236 | 0.119 | 0.256 | 0.057 | |
PLaMo 2 8B | 0.481 | 0.909 | 0.474 | 0.655 | 0.910 | 0.120 | 0.508 | 0.280 | 0.205 | 0.536 | 0.213 | |
Qwen2-7B | 0.472 | 0.875 | 0.463 | 0.372 | 0.899 | 0.172 | 0.524 | 0.209 | 0.195 | 0.587 | 0.422 | |
Qwen2-72B | 0.593 | 0.960 | 0.620 | 0.561 | 0.926 | 0.238 | 0.768 | 0.275 | 0.241 | 0.782 | 0.561 | |
Qwen2.5-0.5B | 0.234 | 0.369 | 0.389 | 0.139 | 0.635 | 0.101 | 0.076 | 0.058 | 0.064 | 0.304 | 0.203 | |
Qwen2.5-1.5B | 0.372 | 0.800 | 0.383 | 0.241 | 0.849 | 0.143 | 0.292 | 0.132 | 0.134 | 0.438 | 0.308 | |
Qwen2.5-3B | 0.442 | 0.847 | 0.475 | 0.306 | 0.878 | 0.176 | 0.460 | 0.180 | 0.167 | 0.529 | 0.404 | |
Qwen2.5-7B | 0.512 | 0.924 | 0.459 | 0.426 | 0.907 | 0.216 | 0.616 | 0.229 | 0.199 | 0.634 | 0.507 | |
Qwen2.5-72B | 0.623 | 0.972 | 0.611 | 0.619 | 0.930 | 0.279 | 0.828 | 0.287 | 0.252 | 0.804 | 0.648 | |
Sarashina2-7B | 0.395 | 0.742 | 0.509 | 0.634 | 0.868 | 0.141 | 0.080 | 0.273 | 0.201 | 0.384 | 0.121 | |
Sarashina2-13B | 0.445 | 0.850 | 0.557 | 0.661 | 0.898 | 0.158 | 0.188 | 0.284 | 0.221 | 0.473 | 0.161 | |
Sarashina2-70B | 0.530 | 0.929 | 0.717 | 0.668 | 0.929 | 0.190 | 0.488 | 0.313 | 0.243 | 0.592 | 0.235 | |
Stockmark-100b | 0.238 | 0.205 | 0.408 | 0.557 | 0.558 | 0.062 | 0.008 | 0.203 | 0.118 | 0.235 | 0.032 | |
Swallow 7B | 0.346 | 0.483 | 0.511 | 0.585 | 0.847 | 0.182 | 0.108 | 0.250 | 0.149 | 0.324 | 0.018 | |
Swallow 13B | 0.415 | 0.764 | 0.507 | 0.643 | 0.893 | 0.215 | 0.208 | 0.272 | 0.178 | 0.439 | 0.027 | |
Swallow 70B | 0.519 | 0.920 | 0.626 | 0.689 | 0.920 | 0.225 | 0.480 | 0.304 | 0.231 | 0.579 | 0.220 | |
Swallow-MS 7B v0.1 | 0.439 | 0.873 | 0.517 | 0.572 | 0.879 | 0.197 | 0.244 | 0.251 | 0.167 | 0.459 | 0.232 | |
Swallow-MX 8x7B v0.1 | 0.506 | 0.922 | 0.533 | 0.577 | 0.917 | 0.263 | 0.444 | 0.272 | 0.209 | 0.565 | 0.358 | |
TinySwallow-1.5B | 0.402 | 0.840 | 0.437 | 0.474 | 0.839 | 0.173 | 0.256 | 0.201 | 0.125 | 0.446 | 0.231 | |
Yi-1.5 6B | 0.354 | 0.658 | 0.380 | 0.226 | 0.829 | 0.198 | 0.240 | 0.130 | 0.147 | 0.423 | 0.313 | |
Yi-1.5 9B | 0.432 | 0.834 | 0.417 | 0.265 | 0.894 | 0.224 | 0.420 | 0.174 | 0.187 | 0.516 | 0.391 | |
Yi-1.5 34B | 0.468 | 0.869 | 0.461 | 0.332 | 0.899 | 0.238 | 0.520 | 0.219 | 0.208 | 0.591 | 0.346 |
Model name | En avg | OpenBookQA | TriviaQA | HellaSwag | SQuAD2 | XWINO | MMLU | GSM8K | MATH | BBH | HumanEval | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Falcon3-1B-Base | 0.376 | 0.316 | 0.296 | 0.458 | 0.501 | 0.816 | 0.449 | 0.337 | 0.140 | 0.323 | 0.125 | |
Falcon3-3B-Base | 0.495 | 0.312 | 0.346 | 0.492 | 0.503 | 0.847 | 0.567 | 0.634 | 0.344 | 0.553 | 0.348 | |
Falcon3-7B-Base | 0.596 | 0.354 | 0.552 | 0.566 | 0.539 | 0.881 | 0.701 | 0.766 | 0.438 | 0.692 | 0.476 | |
Falcon3-10B-Base | 0.639 | 0.368 | 0.579 | 0.596 | 0.603 | 0.901 | 0.732 | 0.802 | 0.492 | 0.776 | 0.543 | |
Gemma 2 2B | 0.439 | 0.342 | 0.552 | 0.552 | 0.501 | 0.890 | 0.530 | 0.249 | 0.176 | 0.415 | 0.188 | |
Gemma 2 9B | 0.597 | 0.382 | 0.718 | 0.626 | 0.506 | 0.907 | 0.706 | 0.688 | 0.338 | 0.704 | 0.390 | |
Gemma 2 27B | 0.655 | 0.412 | 0.780 | 0.675 | 0.549 | 0.921 | 0.754 | 0.757 | 0.438 | 0.760 | 0.508 | |
Gemma 2 Baku 2B | 0.400 | 0.314 | 0.475 | 0.533 | 0.501 | 0.881 | 0.493 | 0.168 | 0.110 | 0.376 | 0.150 | |
Llama 3 8B | 0.542 | 0.380 | 0.712 | 0.612 | 0.502 | 0.905 | 0.651 | 0.487 | 0.180 | 0.620 | 0.376 | |
Llama 3 70B | 0.689 | 0.440 | 0.826 | 0.690 | 0.618 | 0.920 | 0.787 | 0.801 | 0.446 | 0.829 | 0.527 | |
Llama 3 Swallow 8B | 0.523 | 0.350 | 0.656 | 0.590 | 0.519 | 0.901 | 0.615 | 0.483 | 0.182 | 0.598 | 0.337 | |
Llama 3 Swallow 70B | 0.672 | 0.430 | 0.823 | 0.682 | 0.628 | 0.923 | 0.774 | 0.817 | 0.414 | 0.734 | 0.499 | |
Llama 3 Youko 8B | 0.486 | 0.348 | 0.625 | 0.589 | 0.502 | 0.896 | 0.601 | 0.355 | 0.096 | 0.571 | 0.281 | |
Llama 3 Youko 70B | 0.671 | 0.436 | 0.829 | 0.690 | 0.610 | 0.922 | 0.785 | 0.797 | 0.408 | 0.826 | 0.412 | |
Llama 3.1 8B | 0.545 | 0.380 | 0.702 | 0.609 | 0.503 | 0.907 | 0.651 | 0.507 | 0.214 | 0.616 | 0.364 | |
Llama 3.1 70B | 0.671 | 0.450 | 0.829 | 0.690 | 0.605 | 0.920 | 0.786 | 0.798 | 0.434 | 0.655 | 0.546 | |
Llama 3.1 Swallow 8B v0.1 | 0.538 | 0.378 | 0.671 | 0.605 | 0.502 | 0.905 | 0.624 | 0.511 | 0.224 | 0.615 | 0.348 | |
Llama 3.1 Swallow 70B v0.1 | 0.679 | 0.428 | 0.826 | 0.690 | 0.612 | 0.927 | 0.772 | 0.809 | 0.380 | 0.806 | 0.540 | |
Llama 3.1 Swallow 8B v0.2 | 0.539 | 0.382 | 0.651 | 0.596 | 0.513 | 0.904 | 0.622 | 0.521 | 0.228 | 0.605 | 0.366 | |
Llama 3.2 1B | 0.339 | 0.300 | 0.388 | 0.477 | 0.501 | 0.849 | 0.313 | 0.049 | 0.020 | 0.303 | 0.193 | |
Llama 3.2 3B | 0.450 | 0.326 | 0.586 | 0.558 | 0.502 | 0.888 | 0.558 | 0.262 | 0.070 | 0.466 | 0.285 | |
Llama 3.3 Swallow 70B v0.4 | 0.711 | 0.424 | 0.817 | 0.683 | 0.641 | 0.920 | 0.802 | 0.863 | 0.496 | 0.754 | 0.709 | |
llm-jp-3-1.8b | 0.293 | 0.244 | 0.301 | 0.462 | 0.501 | 0.851 | 0.248 | 0.017 | 0.018 | 0.276 | 0.008 | |
llm-jp-3-3.7b | 0.324 | 0.280 | 0.421 | 0.506 | 0.502 | 0.876 | 0.253 | 0.055 | 0.016 | 0.309 | 0.019 | |
llm-jp-3-13b | 0.399 | 0.332 | 0.602 | 0.570 | 0.501 | 0.902 | 0.462 | 0.158 | 0.026 | 0.402 | 0.032 | |
Mistral-Nemo-Base-2407 (12B) | 0.559 | 0.422 | 0.741 | 0.647 | 0.528 | 0.914 | 0.690 | 0.550 | 0.184 | 0.657 | 0.259 | |
Mistral-NeMo-Minitron 8B | 0.572 | 0.406 | 0.728 | 0.621 | 0.525 | 0.915 | 0.694 | 0.585 | 0.202 | 0.658 | 0.382 | |
Mistral-7B-v0.3 | 0.507 | 0.374 | 0.695 | 0.622 | 0.511 | 0.909 | 0.623 | 0.361 | 0.116 | 0.585 | 0.273 | |
Mixtral-8x22B-v0.1 | 0.652 | 0.420 | 0.833 | 0.696 | 0.593 | 0.919 | 0.772 | 0.754 | 0.414 | 0.811 | 0.309 | |
PLaMo 2 1B | 0.274 | 0.280 | 0.129 | 0.425 | 0.501 | 0.807 | 0.294 | 0.072 | 0.034 | 0.122 | 0.080 | |
PLaMo 2 8B | 0.474 | 0.346 | 0.584 | 0.560 | 0.511 | 0.890 | 0.575 | 0.550 | 0.200 | 0.260 | 0.260 | |
Qwen2-7B | 0.602 | 0.374 | 0.610 | 0.602 | 0.574 | 0.891 | 0.705 | 0.781 | 0.492 | 0.530 | 0.460 | |
Qwen2-72B | 0.702 | 0.418 | 0.790 | 0.677 | 0.673 | 0.915 | 0.842 | 0.893 | 0.560 | 0.643 | 0.608 | |
Qwen2.5-0.5B | 0.365 | 0.266 | 0.190 | 0.399 | 0.501 | 0.768 | 0.479 | 0.341 | 0.148 | 0.277 | 0.277 | |
Qwen2.5-1.5B | 0.490 | 0.342 | 0.397 | 0.499 | 0.506 | 0.851 | 0.610 | 0.611 | 0.314 | 0.413 | 0.356 | |
Qwen2.5-3B | 0.534 | 0.360 | 0.504 | 0.553 | 0.541 | 0.872 | 0.657 | 0.580 | 0.440 | 0.442 | 0.387 | |
Qwen2.5-7B | 0.630 | 0.392 | 0.601 | 0.600 | 0.618 | 0.888 | 0.742 | 0.832 | 0.510 | 0.562 | 0.554 | |
Qwen2.5-72B | 0.709 | 0.416 | 0.760 | 0.685 | 0.693 | 0.901 | 0.861 | 0.870 | 0.626 | 0.727 | 0.554 | |
Sarashina2-7B | 0.383 | 0.346 | 0.479 | 0.532 | 0.501 | 0.892 | 0.425 | 0.101 | 0.034 | 0.373 | 0.146 | |
Sarashina2-13B | 0.418 | 0.340 | 0.548 | 0.562 | 0.501 | 0.896 | 0.496 | 0.158 | 0.036 | 0.442 | 0.198 | |
Sarashina2-70B | 0.491 | 0.388 | 0.537 | 0.628 | 0.675 | 0.917 | 0.630 | 0.011 | 0.206 | 0.639 | 0.281 | |
Stockmark-100b | 0.302 | 0.278 | 0.366 | 0.458 | 0.501 | 0.820 | 0.258 | 0.017 | 0.014 | 0.259 | 0.046 | |
Swallow 7B | 0.363 | 0.312 | 0.491 | 0.527 | 0.501 | 0.885 | 0.391 | 0.103 | 0.020 | 0.354 | 0.041 | |
Swallow 13B | 0.412 | 0.344 | 0.580 | 0.560 | 0.502 | 0.902 | 0.501 | 0.197 | 0.024 | 0.430 | 0.080 | |
Swallow 70B | 0.543 | 0.416 | 0.761 | 0.643 | 0.522 | 0.920 | 0.659 | 0.503 | 0.108 | 0.655 | 0.240 | |
Swallow-MS 7B v0.1 | 0.461 | 0.352 | 0.599 | 0.579 | 0.501 | 0.901 | 0.548 | 0.268 | 0.096 | 0.491 | 0.270 | |
Swallow-MX 8x7B v0.1 | 0.589 | 0.348 | 0.773 | 0.651 | 0.538 | 0.919 | 0.692 | 0.574 | 0.298 | 0.686 | 0.410 | |
TinySwallow-1.5B | 0.413 | 0.308 | 0.332 | 0.468 | 0.501 | 0.850 | 0.546 | 0.379 | 0.162 | 0.328 | 0.254 | |
Yi-1.5 6B | 0.540 | 0.344 | 0.593 | 0.575 | 0.651 | 0.898 | 0.636 | 0.522 | 0.244 | 0.583 | 0.352 | |
Yi-1.5 9B | 0.592 | 0.390 | 0.619 | 0.601 | 0.693 | 0.902 | 0.696 | 0.620 | 0.300 | 0.710 | 0.384 | |
Yi-1.5 34B | 0.650 | 0.402 | 0.708 | 0.662 | 0.754 | 0.910 | 0.774 | 0.743 | 0.394 | 0.763 | 0.385 |