Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -319,6 +319,518 @@ def download_all_data():
|
|
| 319 |
# --------------------------------------------------------------------
|
| 320 |
# This is your larger dataset, rank = 44..105
|
| 321 |
benchmark_data = [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 322 |
{
|
| 323 |
"rank": 1,
|
| 324 |
"name": "suayptalha/Lamarckvergence-14B",
|
|
|
|
| 319 |
# --------------------------------------------------------------------
|
| 320 |
# This is your larger dataset, rank = 44..105
|
| 321 |
benchmark_data = [
|
| 322 |
+
{
|
| 323 |
+
"Model Rank": "1",
|
| 324 |
+
"Icon": "ð¤",
|
| 325 |
+
"Model Name": "wanlige/li-14b-v0.4",
|
| 326 |
+
"Average Score": "43.66 %",
|
| 327 |
+
"IFEval Score": "81.33 %",
|
| 328 |
+
"BBH Score": "50.38 %",
|
| 329 |
+
"MATH Score": "55.74 %",
|
| 330 |
+
"GPQA Score": "11.86 %",
|
| 331 |
+
"MUSR Score": "16.35 %",
|
| 332 |
+
"MMLU-PRO Score": "46.30 %",
|
| 333 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 334 |
+
"Model Precision": "bfloat16",
|
| 335 |
+
"Model Parameters": "14.77B",
|
| 336 |
+
"Chat Template Use": "Yes"
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"Model Rank": "2",
|
| 340 |
+
"Icon": "ð¤",
|
| 341 |
+
"Model Name": "suayptalha/Lamarckvergence-14B",
|
| 342 |
+
"Average Score": "43.32 %",
|
| 343 |
+
"IFEval Score": "76.56 %",
|
| 344 |
+
"BBH Score": "50.33 %",
|
| 345 |
+
"MATH Score": "54.00 %",
|
| 346 |
+
"GPQA Score": "15.10 %",
|
| 347 |
+
"MUSR Score": "16.34 %",
|
| 348 |
+
"MMLU-PRO Score": "47.59 %",
|
| 349 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 350 |
+
"Model Precision": "bfloat16",
|
| 351 |
+
"Model Parameters": "14.766B",
|
| 352 |
+
"Chat Template Use": "Yes"
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"Model Rank": "3",
|
| 356 |
+
"Icon": "ð¤",
|
| 357 |
+
"Model Name": "wanlige/li-14b-v0.4-slerp0.1",
|
| 358 |
+
"Average Score": "42.91 %",
|
| 359 |
+
"IFEval Score": "79.23 %",
|
| 360 |
+
"BBH Score": "50.88 %",
|
| 361 |
+
"MATH Score": "53.32 %",
|
| 362 |
+
"GPQA Score": "14.54 %",
|
| 363 |
+
"MUSR Score": "11.75 %",
|
| 364 |
+
"MMLU-PRO Score": "47.71 %",
|
| 365 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 366 |
+
"Model Precision": "bfloat16",
|
| 367 |
+
"Model Parameters": "14.766B",
|
| 368 |
+
"Chat Template Use": "Yes"
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"Model Rank": "4",
|
| 372 |
+
"Icon": "ð¬",
|
| 373 |
+
"Model Name": "sthenno-com/miscii-14b-0218",
|
| 374 |
+
"Average Score": "42.90 %",
|
| 375 |
+
"IFEval Score": "76.56 %",
|
| 376 |
+
"BBH Score": "50.64 %",
|
| 377 |
+
"MATH Score": "51.44 %",
|
| 378 |
+
"GPQA Score": "17.79 %",
|
| 379 |
+
"MUSR Score": "13.21 %",
|
| 380 |
+
"MMLU-PRO Score": "47.75 %",
|
| 381 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 382 |
+
"Model Precision": "bfloat16",
|
| 383 |
+
"Model Parameters": "14.766B",
|
| 384 |
+
"Chat Template Use": "Yes"
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"Model Rank": "5",
|
| 388 |
+
"Icon": "├░┬╢",
|
| 389 |
+
"Model Name": "sthenno/tempesthenno-ppo-ckpt40",
|
| 390 |
+
"Average Score": "42.74 %",
|
| 391 |
+
"IFEval Score": "79.23 %",
|
| 392 |
+
"BBH Score": "50.57 %",
|
| 393 |
+
"MATH Score": "47.36 %",
|
| 394 |
+
"GPQA Score": "17.00 %",
|
| 395 |
+
"MUSR Score": "14.56 %",
|
| 396 |
+
"MMLU-PRO Score": "47.69 %",
|
| 397 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 398 |
+
"Model Precision": "bfloat16",
|
| 399 |
+
"Model Parameters": "14.766B",
|
| 400 |
+
"Chat Template Use": "Yes"
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"Model Rank": "6",
|
| 404 |
+
"Icon": "ð¬",
|
| 405 |
+
"Model Name": "tanliboy/lambda-qwen2.5-14b-dpo-test",
|
| 406 |
+
"Average Score": "42.62 %",
|
| 407 |
+
"IFEval Score": "82.31 %",
|
| 408 |
+
"BBH Score": "48.45 %",
|
| 409 |
+
"MATH Score": "54.61 %",
|
| 410 |
+
"GPQA Score": "14.99 %",
|
| 411 |
+
"MUSR Score": "12.59 %",
|
| 412 |
+
"MMLU-PRO Score": "42.75 %",
|
| 413 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 414 |
+
"Model Precision": "bfloat16",
|
| 415 |
+
"Model Parameters": "14.77B",
|
| 416 |
+
"Chat Template Use": "Yes"
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"Model Rank": "7",
|
| 420 |
+
"Icon": "├░┬╢",
|
| 421 |
+
"Model Name": "sthenno/tempesthenno-nuslerp-001",
|
| 422 |
+
"Average Score": "42.59 %",
|
| 423 |
+
"IFEval Score": "79.26 %",
|
| 424 |
+
"BBH Score": "51.04 %",
|
| 425 |
+
"MATH Score": "47.58 %",
|
| 426 |
+
"GPQA Score": "16.44 %",
|
| 427 |
+
"MUSR Score": "13.88 %",
|
| 428 |
+
"MMLU-PRO Score": "47.30 %",
|
| 429 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 430 |
+
"Model Precision": "bfloat16",
|
| 431 |
+
"Model Parameters": "14.766B",
|
| 432 |
+
"Chat Template Use": "Yes"
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"Model Rank": "8",
|
| 436 |
+
"Icon": "ð¤",
|
| 437 |
+
"Model Name": "YOYO-AI/Qwen2.5-14B-1M-YOYO-V3",
|
| 438 |
+
"Average Score": "42.56 %",
|
| 439 |
+
"IFEval Score": "83.98 %",
|
| 440 |
+
"BBH Score": "49.47 %",
|
| 441 |
+
"MATH Score": "53.55 %",
|
| 442 |
+
"GPQA Score": "10.51 %",
|
| 443 |
+
"MUSR Score": "11.10 %",
|
| 444 |
+
"MMLU-PRO Score": "46.74 %",
|
| 445 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 446 |
+
"Model Precision": "float16",
|
| 447 |
+
"Model Parameters": "14.766B",
|
| 448 |
+
"Chat Template Use": "Yes"
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"Model Rank": "9",
|
| 452 |
+
"Icon": "├░┬╢",
|
| 453 |
+
"Model Name": "Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4",
|
| 454 |
+
"Average Score": "42.55 %",
|
| 455 |
+
"IFEval Score": "82.92 %",
|
| 456 |
+
"BBH Score": "48.05 %",
|
| 457 |
+
"MATH Score": "54.23 %",
|
| 458 |
+
"GPQA Score": "12.30 %",
|
| 459 |
+
"MUSR Score": "13.15 %",
|
| 460 |
+
"MMLU-PRO Score": "44.65 %",
|
| 461 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 462 |
+
"Model Precision": "bfloat16",
|
| 463 |
+
"Model Parameters": "14.77B",
|
| 464 |
+
"Chat Template Use": "Yes"
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"Model Rank": "10",
|
| 468 |
+
"Icon": "ð¤",
|
| 469 |
+
"Model Name": "djuna/Q2.5-Veltha-14B",
|
| 470 |
+
"Average Score": "42.52 %",
|
| 471 |
+
"IFEval Score": "82.92 %",
|
| 472 |
+
"BBH Score": "49.75 %",
|
| 473 |
+
"MATH Score": "47.89 %",
|
| 474 |
+
"GPQA Score": "14.54 %",
|
| 475 |
+
"MUSR Score": "12.26 %",
|
| 476 |
+
"MMLU-PRO Score": "47.76 %",
|
| 477 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 478 |
+
"Model Precision": "bfloat16",
|
| 479 |
+
"Model Parameters": "14.766B",
|
| 480 |
+
"Chat Template Use": "Yes"
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"Model Rank": "11",
|
| 484 |
+
"Icon": "├░┬╢",
|
| 485 |
+
"Model Name": "arcee-ai/Virtuoso-Small-v2",
|
| 486 |
+
"Average Score": "42.48 %",
|
| 487 |
+
"IFEval Score": "82.73 %",
|
| 488 |
+
"BBH Score": "50.95 %",
|
| 489 |
+
"MATH Score": "46.60 %",
|
| 490 |
+
"GPQA Score": "13.76 %",
|
| 491 |
+
"MUSR Score": "14.28 %",
|
| 492 |
+
"MMLU-PRO Score": "46.53 %",
|
| 493 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 494 |
+
"Model Precision": "bfloat16",
|
| 495 |
+
"Model Parameters": "14.766B",
|
| 496 |
+
"Chat Template Use": "Yes"
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"Model Rank": "12",
|
| 500 |
+
"Icon": "ð¤",
|
| 501 |
+
"Model Name": "YOYO-AI/Qwen2.5-14B-YOYO-V4-p1",
|
| 502 |
+
"Average Score": "42.46 %",
|
| 503 |
+
"IFEval Score": "82.03 %",
|
| 504 |
+
"BBH Score": "50.25 %",
|
| 505 |
+
"MATH Score": "53.32 %",
|
| 506 |
+
"GPQA Score": "12.75 %",
|
| 507 |
+
"MUSR Score": "11.73 %",
|
| 508 |
+
"MMLU-PRO Score": "44.67 %",
|
| 509 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 510 |
+
"Model Precision": "float16",
|
| 511 |
+
"Model Parameters": "14.766B",
|
| 512 |
+
"Chat Template Use": "Yes"
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"Model Rank": "13",
|
| 516 |
+
"Icon": "ð¬",
|
| 517 |
+
"Model Name": "jpacifico/Chocolatine-14B-Instruct-DPO-v1.3",
|
| 518 |
+
"Average Score": "42.42 %",
|
| 519 |
+
"IFEval Score": "70.40 %",
|
| 520 |
+
"BBH Score": "54.85 %",
|
| 521 |
+
"MATH Score": "56.19 %",
|
| 522 |
+
"GPQA Score": "12.19 %",
|
| 523 |
+
"MUSR Score": "12.29 %",
|
| 524 |
+
"MMLU-PRO Score": "48.60 %",
|
| 525 |
+
"Model Architecture": "Phi3ForCausalLM",
|
| 526 |
+
"Model Precision": "float16",
|
| 527 |
+
"Model Parameters": "14.66B",
|
| 528 |
+
"Chat Template Use": "Yes"
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"Model Rank": "14",
|
| 532 |
+
"Icon": "ð¬",
|
| 533 |
+
"Model Name": "sthenno-com/miscii-14b-1028",
|
| 534 |
+
"Average Score": "42.38 %",
|
| 535 |
+
"IFEval Score": "82.37 %",
|
| 536 |
+
"BBH Score": "49.26 %",
|
| 537 |
+
"MATH Score": "50.30 %",
|
| 538 |
+
"GPQA Score": "14.21 %",
|
| 539 |
+
"MUSR Score": "12.00 %",
|
| 540 |
+
"MMLU-PRO Score": "46.14 %",
|
| 541 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 542 |
+
"Model Precision": "bfloat16",
|
| 543 |
+
"Model Parameters": "14.77B",
|
| 544 |
+
"Chat Template Use": "Yes"
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"Model Rank": "15",
|
| 548 |
+
"Icon": "ð¬",
|
| 549 |
+
"Model Name": "sthenno-com/miscii-14b-1225",
|
| 550 |
+
"Average Score": "42.35 %",
|
| 551 |
+
"IFEval Score": "78.78 %",
|
| 552 |
+
"BBH Score": "50.91 %",
|
| 553 |
+
"MATH Score": "45.17 %",
|
| 554 |
+
"GPQA Score": "17.00 %",
|
| 555 |
+
"MUSR Score": "14.77 %",
|
| 556 |
+
"MMLU-PRO Score": "47.46 %",
|
| 557 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 558 |
+
"Model Precision": "bfloat16",
|
| 559 |
+
"Model Parameters": "14.766B",
|
| 560 |
+
"Chat Template Use": "Yes"
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"Model Rank": "16",
|
| 564 |
+
"Icon": "├░┬╢",
|
| 565 |
+
"Model Name": "prithivMLmods/Sombrero-Opus-14B-Elite5",
|
| 566 |
+
"Average Score": "42.32 %",
|
| 567 |
+
"IFEval Score": "78.81 %",
|
| 568 |
+
"BBH Score": "50.17 %",
|
| 569 |
+
"MATH Score": "53.55 %",
|
| 570 |
+
"GPQA Score": "11.52 %",
|
| 571 |
+
"MUSR Score": "13.22 %",
|
| 572 |
+
"MMLU-PRO Score": "46.67 %",
|
| 573 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 574 |
+
"Model Precision": "float16",
|
| 575 |
+
"Model Parameters": "14.766B",
|
| 576 |
+
"Chat Template Use": "Yes"
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"Model Rank": "17",
|
| 580 |
+
"Icon": "ð¤",
|
| 581 |
+
"Model Name": "Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8",
|
| 582 |
+
"Average Score": "42.26 %",
|
| 583 |
+
"IFEval Score": "73.84 %",
|
| 584 |
+
"BBH Score": "49.31 %",
|
| 585 |
+
"MATH Score": "41.69 %",
|
| 586 |
+
"GPQA Score": "18.23 %",
|
| 587 |
+
"MUSR Score": "21.96 %",
|
| 588 |
+
"MMLU-PRO Score": "48.50 %",
|
| 589 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 590 |
+
"Model Precision": "bfloat16",
|
| 591 |
+
"Model Parameters": "14.766B",
|
| 592 |
+
"Chat Template Use": "No"
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"Model Rank": "18",
|
| 596 |
+
"Icon": "├░┬╢",
|
| 597 |
+
"Model Name": "prithivMLmods/Equuleus-Opus-14B-Exp",
|
| 598 |
+
"Average Score": "42.20 %",
|
| 599 |
+
"IFEval Score": "70.01 %",
|
| 600 |
+
"BBH Score": "48.62 %",
|
| 601 |
+
"MATH Score": "45.85 %",
|
| 602 |
+
"GPQA Score": "18.23 %",
|
| 603 |
+
"MUSR Score": "21.90 %",
|
| 604 |
+
"MMLU-PRO Score": "48.60 %",
|
| 605 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 606 |
+
"Model Precision": "bfloat16",
|
| 607 |
+
"Model Parameters": "14.766B",
|
| 608 |
+
"Chat Template Use": "No"
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"Model Rank": "19",
|
| 612 |
+
"Icon": "├░┬╢",
|
| 613 |
+
"Model Name": "rombodawg/Rombos-LLM-V2.6-Qwen-14b",
|
| 614 |
+
"Average Score": "42.20 %",
|
| 615 |
+
"IFEval Score": "84.32 %",
|
| 616 |
+
"BBH Score": "49.28 %",
|
| 617 |
+
"MATH Score": "52.11 %",
|
| 618 |
+
"GPQA Score": "11.19 %",
|
| 619 |
+
"MUSR Score": "12.29 %",
|
| 620 |
+
"MMLU-PRO Score": "44.01 %",
|
| 621 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 622 |
+
"Model Precision": "bfloat16",
|
| 623 |
+
"Model Parameters": "14.77B",
|
| 624 |
+
"Chat Template Use": "Yes"
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"Model Rank": "20",
|
| 628 |
+
"Icon": "ð¤",
|
| 629 |
+
"Model Name": "nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B",
|
| 630 |
+
"Average Score": "42.16 %",
|
| 631 |
+
"IFEval Score": "78.36 %",
|
| 632 |
+
"BBH Score": "48.52 %",
|
| 633 |
+
"MATH Score": "50.45 %",
|
| 634 |
+
"GPQA Score": "13.98 %",
|
| 635 |
+
"MUSR Score": "14.88 %",
|
| 636 |
+
"MMLU-PRO Score": "46.79 %",
|
| 637 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 638 |
+
"Model Precision": "bfloat16",
|
| 639 |
+
"Model Parameters": "14.77B",
|
| 640 |
+
"Chat Template Use": "Yes"
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"Model Rank": "21",
|
| 644 |
+
"Icon": "ð¤",
|
| 645 |
+
"Model Name": "sometimesanotion/LamarckInfusion-14B-v1",
|
| 646 |
+
"Average Score": "42.06 %",
|
| 647 |
+
"IFEval Score": "71.98 %",
|
| 648 |
+
"BBH Score": "50.35 %",
|
| 649 |
+
"MATH Score": "41.69 %",
|
| 650 |
+
"GPQA Score": "18.79 %",
|
| 651 |
+
"MUSR Score": "20.90 %",
|
| 652 |
+
"MMLU-PRO Score": "48.63 %",
|
| 653 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 654 |
+
"Model Precision": "bfloat16",
|
| 655 |
+
"Model Parameters": "14.766B",
|
| 656 |
+
"Chat Template Use": "No"
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"Model Rank": "22",
|
| 660 |
+
"Icon": "ð¤",
|
| 661 |
+
"Model Name": "tensopolis/virtuoso-small-v2-tensopolis-v1",
|
| 662 |
+
"Average Score": "41.99 %",
|
| 663 |
+
"IFEval Score": "82.40 %",
|
| 664 |
+
"BBH Score": "50.53 %",
|
| 665 |
+
"MATH Score": "46.53 %",
|
| 666 |
+
"GPQA Score": "12.53 %",
|
| 667 |
+
"MUSR Score": "13.88 %",
|
| 668 |
+
"MMLU-PRO Score": "46.07 %",
|
| 669 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 670 |
+
"Model Precision": "bfloat16",
|
| 671 |
+
"Model Parameters": "14.766B",
|
| 672 |
+
"Chat Template Use": "Yes"
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"Model Rank": "23",
|
| 676 |
+
"Icon": "ð¤",
|
| 677 |
+
"Model Name": "Quazim0t0/Fugazi14b",
|
| 678 |
+
"Average Score": "41.94 %",
|
| 679 |
+
"IFEval Score": "69.98 %",
|
| 680 |
+
"BBH Score": "56.09 %",
|
| 681 |
+
"MATH Score": "46.53 %",
|
| 682 |
+
"GPQA Score": "13.53 %",
|
| 683 |
+
"MUSR Score": "16.42 %",
|
| 684 |
+
"MMLU-PRO Score": "49.08 %",
|
| 685 |
+
"Model Architecture": "LlamaForCausalLM",
|
| 686 |
+
"Model Precision": "bfloat16",
|
| 687 |
+
"Model Parameters": "14.66B",
|
| 688 |
+
"Chat Template Use": "Yes"
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"Model Rank": "24",
|
| 692 |
+
"Icon": "├░┬╢",
|
| 693 |
+
"Model Name": "1024m/QWEN-14B-B100",
|
| 694 |
+
"Average Score": "41.92 %",
|
| 695 |
+
"IFEval Score": "77.62 %",
|
| 696 |
+
"BBH Score": "49.78 %",
|
| 697 |
+
"MATH Score": "54.38 %",
|
| 698 |
+
"GPQA Score": "13.42 %",
|
| 699 |
+
"MUSR Score": "9.88 %",
|
| 700 |
+
"MMLU-PRO Score": "46.43 %",
|
| 701 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 702 |
+
"Model Precision": "bfloat16",
|
| 703 |
+
"Model Parameters": "14.77B",
|
| 704 |
+
"Chat Template Use": "Yes"
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"Model Rank": "25",
|
| 708 |
+
"Icon": "├░┬╢",
|
| 709 |
+
"Model Name": "Sakalti/Saka-14B",
|
| 710 |
+
"Average Score": "41.91 %",
|
| 711 |
+
"IFEval Score": "71.74 %",
|
| 712 |
+
"BBH Score": "49.72 %",
|
| 713 |
+
"MATH Score": "40.94 %",
|
| 714 |
+
"GPQA Score": "19.46 %",
|
| 715 |
+
"MUSR Score": "20.74 %",
|
| 716 |
+
"MMLU-PRO Score": "48.84 %",
|
| 717 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 718 |
+
"Model Precision": "float16",
|
| 719 |
+
"Model Parameters": "14.766B",
|
| 720 |
+
"Chat Template Use": "No"
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"Model Rank": "26",
|
| 724 |
+
"Icon": "├░┬╢",
|
| 725 |
+
"Model Name": "prithivMLmods/Sombrero-Opus-14B-Elite6",
|
| 726 |
+
"Average Score": "41.88 %",
|
| 727 |
+
"IFEval Score": "72.26 %",
|
| 728 |
+
"BBH Score": "49.60 %",
|
| 729 |
+
"MATH Score": "40.79 %",
|
| 730 |
+
"GPQA Score": "19.13 %",
|
| 731 |
+
"MUSR Score": "20.74 %",
|
| 732 |
+
"MMLU-PRO Score": "48.78 %",
|
| 733 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 734 |
+
"Model Precision": "bfloat16",
|
| 735 |
+
"Model Parameters": "14.766B",
|
| 736 |
+
"Chat Template Use": "No"
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"Model Rank": "27",
|
| 740 |
+
"Icon": "ð¤",
|
| 741 |
+
"Model Name": "YOYO-AI/Qwen2.5-14B-YOYO-latest-V2",
|
| 742 |
+
"Average Score": "41.85 %",
|
| 743 |
+
"IFEval Score": "77.71 %",
|
| 744 |
+
"BBH Score": "47.30 %",
|
| 745 |
+
"MATH Score": "51.59 %",
|
| 746 |
+
"GPQA Score": "13.87 %",
|
| 747 |
+
"MUSR Score": "13.68 %",
|
| 748 |
+
"MMLU-PRO Score": "46.93 %",
|
| 749 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 750 |
+
"Model Precision": "float16",
|
| 751 |
+
"Model Parameters": "14.766B",
|
| 752 |
+
"Chat Template Use": "Yes"
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"Model Rank": "28",
|
| 756 |
+
"Icon": "ð¬",
|
| 757 |
+
"Model Name": "Tsunami-th/Tsunami-1.0-14B-Instruct",
|
| 758 |
+
"Average Score": "41.84 %",
|
| 759 |
+
"IFEval Score": "78.29 %",
|
| 760 |
+
"BBH Score": "49.15 %",
|
| 761 |
+
"MATH Score": "45.85 %",
|
| 762 |
+
"GPQA Score": "14.21 %",
|
| 763 |
+
"MUSR Score": "16.34 %",
|
| 764 |
+
"MMLU-PRO Score": "47.21 %",
|
| 765 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 766 |
+
"Model Precision": "bfloat16",
|
| 767 |
+
"Model Parameters": "14.77B",
|
| 768 |
+
"Chat Template Use": "Yes"
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"Model Rank": "29",
|
| 772 |
+
"Icon": "├░┬╢",
|
| 773 |
+
"Model Name": "sthenno/tempesthenno-kto-0205-ckpt80",
|
| 774 |
+
"Average Score": "41.79 %",
|
| 775 |
+
"IFEval Score": "80.54 %",
|
| 776 |
+
"BBH Score": "50.64 %",
|
| 777 |
+
"MATH Score": "45.92 %",
|
| 778 |
+
"GPQA Score": "13.09 %",
|
| 779 |
+
"MUSR Score": "12.93 %",
|
| 780 |
+
"MMLU-PRO Score": "47.62 %",
|
| 781 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 782 |
+
"Model Precision": "bfloat16",
|
| 783 |
+
"Model Parameters": "14.766B",
|
| 784 |
+
"Chat Template Use": "No"
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"Model Rank": "30",
|
| 788 |
+
"Icon": "ð¤",
|
| 789 |
+
"Model Name": "sometimesanotion/Lamarck-14B-v0.7-rc4",
|
| 790 |
+
"Average Score": "41.79 %",
|
| 791 |
+
"IFEval Score": "72.11 %",
|
| 792 |
+
"BBH Score": "49.85 %",
|
| 793 |
+
"MATH Score": "40.26 %",
|
| 794 |
+
"GPQA Score": "18.57 %",
|
| 795 |
+
"MUSR Score": "21.07 %",
|
| 796 |
+
"MMLU-PRO Score": "48.89 %",
|
| 797 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 798 |
+
"Model Precision": "bfloat16",
|
| 799 |
+
"Model Parameters": "14.766B",
|
| 800 |
+
"Chat Template Use": "No"
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"Model Rank": "31",
|
| 804 |
+
"Icon": "├░┬╢",
|
| 805 |
+
"Model Name": "prithivMLmods/Porpoise-Opus-14B-Exp",
|
| 806 |
+
"Average Score": "41.77 %",
|
| 807 |
+
"IFEval Score": "70.98 %",
|
| 808 |
+
"BBH Score": "49.95 %",
|
| 809 |
+
"MATH Score": "40.41 %",
|
| 810 |
+
"GPQA Score": "19.13 %",
|
| 811 |
+
"MUSR Score": "21.30 %",
|
| 812 |
+
"MMLU-PRO Score": "48.85 %",
|
| 813 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 814 |
+
"Model Precision": "bfloat16",
|
| 815 |
+
"Model Parameters": "14.766B",
|
| 816 |
+
"Chat Template Use": "No"
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"Model Rank": "32",
|
| 820 |
+
"Icon": "ð¤",
|
| 821 |
+
"Model Name": "CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES",
|
| 822 |
+
"Average Score": "41.77 %",
|
| 823 |
+
"IFEval Score": "82.40 %",
|
| 824 |
+
"BBH Score": "48.20 %",
|
| 825 |
+
"MATH Score": "53.17 %",
|
| 826 |
+
"GPQA Score": "9.96 %",
|
| 827 |
+
"MUSR Score": "12.65 %",
|
| 828 |
+
"MMLU-PRO Score": "44.21 %",
|
| 829 |
+
"Model Architecture": "Qwen2ForCausalLM",
|
| 830 |
+
"Model Precision": "bfloat16",
|
| 831 |
+
"Model Parameters": "14.77B",
|
| 832 |
+
"Chat Template Use": "Yes"
|
| 833 |
+
},
|
| 834 |
{
|
| 835 |
"rank": 1,
|
| 836 |
"name": "suayptalha/Lamarckvergence-14B",
|