Spaces:
Running
Running
Commit
·
acd6553
1
Parent(s):
8055678
Add Magistral and Qwen3-Coder hehe
Browse files- results/parse.py +2 -2
- results/results_icarus.json +49 -49
- results/results_verilator.json +50 -50
results/parse.py
CHANGED
@@ -165,13 +165,13 @@ model_details = {
|
|
165 |
"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
166 |
480,
|
167 |
"Coding",
|
168 |
-
"
|
169 |
),
|
170 |
"Magistral Small 2506": (
|
171 |
"https://huggingface.co/mistralai/Magistral-Small-2506",
|
172 |
23.6,
|
173 |
"General",
|
174 |
-
"
|
175 |
),
|
176 |
}
|
177 |
|
|
|
165 |
"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
166 |
480,
|
167 |
"Coding",
|
168 |
+
"V2",
|
169 |
),
|
170 |
"Magistral Small 2506": (
|
171 |
"https://huggingface.co/mistralai/Magistral-Small-2506",
|
172 |
23.6,
|
173 |
"General",
|
174 |
+
"V2",
|
175 |
),
|
176 |
}
|
177 |
|
results/results_icarus.json
CHANGED
@@ -507,7 +507,7 @@
|
|
507 |
"Result": 96.41,
|
508 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
509 |
"Params": 480,
|
510 |
-
"Release": "
|
511 |
},
|
512 |
{
|
513 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -517,7 +517,7 @@
|
|
517 |
"Result": 86.38,
|
518 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
519 |
"Params": 480,
|
520 |
-
"Release": "
|
521 |
},
|
522 |
{
|
523 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -527,7 +527,7 @@
|
|
527 |
"Result": 65.38,
|
528 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
529 |
"Params": 480,
|
530 |
-
"Release": "
|
531 |
},
|
532 |
{
|
533 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -537,7 +537,7 @@
|
|
537 |
"Result": 59.57,
|
538 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
539 |
"Params": 480,
|
540 |
-
"Release": "
|
541 |
},
|
542 |
{
|
543 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -547,7 +547,7 @@
|
|
547 |
"Result": 64.74,
|
548 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
549 |
"Params": 480,
|
550 |
-
"Release": "
|
551 |
},
|
552 |
{
|
553 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -557,7 +557,7 @@
|
|
557 |
"Result": 53.62,
|
558 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
559 |
"Params": 480,
|
560 |
-
"Release": "
|
561 |
},
|
562 |
{
|
563 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -567,7 +567,7 @@
|
|
567 |
"Result": 64.09,
|
568 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
569 |
"Params": 480,
|
570 |
-
"Release": "
|
571 |
},
|
572 |
{
|
573 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -577,7 +577,7 @@
|
|
577 |
"Result": 52.85,
|
578 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
579 |
"Params": 480,
|
580 |
-
"Release": "
|
581 |
},
|
582 |
{
|
583 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -587,7 +587,7 @@
|
|
587 |
"Result": 61.91,
|
588 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
589 |
"Params": 480,
|
590 |
-
"Release": "
|
591 |
},
|
592 |
{
|
593 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -597,7 +597,7 @@
|
|
597 |
"Result": 53.03,
|
598 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
599 |
"Params": 480,
|
600 |
-
"Release": "
|
601 |
},
|
602 |
{
|
603 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -607,7 +607,7 @@
|
|
607 |
"Result": 62.93,
|
608 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
609 |
"Params": 480,
|
610 |
-
"Release": "
|
611 |
},
|
612 |
{
|
613 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -617,7 +617,7 @@
|
|
617 |
"Result": 51.81,
|
618 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
619 |
"Params": 480,
|
620 |
-
"Release": "
|
621 |
},
|
622 |
{
|
623 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -627,7 +627,7 @@
|
|
627 |
"Result": 38.88,
|
628 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
629 |
"Params": 480,
|
630 |
-
"Release": "
|
631 |
},
|
632 |
{
|
633 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -637,7 +637,7 @@
|
|
637 |
"Result": 84.1,
|
638 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
639 |
"Params": 480,
|
640 |
-
"Release": "
|
641 |
},
|
642 |
{
|
643 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -647,7 +647,7 @@
|
|
647 |
"Result": 100.0,
|
648 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
649 |
"Params": 480,
|
650 |
-
"Release": "
|
651 |
},
|
652 |
{
|
653 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -657,7 +657,7 @@
|
|
657 |
"Result": 58.85,
|
658 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
659 |
"Params": 480,
|
660 |
-
"Release": "
|
661 |
},
|
662 |
{
|
663 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -667,7 +667,7 @@
|
|
667 |
"Result": 75.29,
|
668 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
669 |
"Params": 480,
|
670 |
-
"Release": "
|
671 |
},
|
672 |
{
|
673 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -677,7 +677,7 @@
|
|
677 |
"Result": 58.46,
|
678 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
679 |
"Params": 480,
|
680 |
-
"Release": "
|
681 |
},
|
682 |
{
|
683 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -687,7 +687,7 @@
|
|
687 |
"Result": 75.29,
|
688 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
689 |
"Params": 480,
|
690 |
-
"Release": "
|
691 |
},
|
692 |
{
|
693 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -697,7 +697,7 @@
|
|
697 |
"Result": 57.05,
|
698 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
699 |
"Params": 480,
|
700 |
-
"Release": "
|
701 |
},
|
702 |
{
|
703 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -707,7 +707,7 @@
|
|
707 |
"Result": 69.63,
|
708 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
709 |
"Params": 480,
|
710 |
-
"Release": "
|
711 |
},
|
712 |
{
|
713 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -717,7 +717,7 @@
|
|
717 |
"Result": 55.54,
|
718 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
719 |
"Params": 480,
|
720 |
-
"Release": "
|
721 |
},
|
722 |
{
|
723 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -727,7 +727,7 @@
|
|
727 |
"Result": 73.95,
|
728 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
729 |
"Params": 480,
|
730 |
-
"Release": "
|
731 |
},
|
732 |
{
|
733 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -737,7 +737,7 @@
|
|
737 |
"Result": 55.79,
|
738 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
739 |
"Params": 480,
|
740 |
-
"Release": "
|
741 |
},
|
742 |
{
|
743 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -747,7 +747,7 @@
|
|
747 |
"Result": 76.76,
|
748 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
749 |
"Params": 480,
|
750 |
-
"Release": "
|
751 |
},
|
752 |
{
|
753 |
"Model": "Llama 3.1 405B",
|
@@ -2277,7 +2277,7 @@
|
|
2277 |
"Result": 42.95,
|
2278 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2279 |
"Params": 23.6,
|
2280 |
-
"Release": "
|
2281 |
},
|
2282 |
{
|
2283 |
"Model": "Magistral Small 2506",
|
@@ -2287,7 +2287,7 @@
|
|
2287 |
"Result": 43.4,
|
2288 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2289 |
"Params": 23.6,
|
2290 |
-
"Release": "
|
2291 |
},
|
2292 |
{
|
2293 |
"Model": "Magistral Small 2506",
|
@@ -2297,7 +2297,7 @@
|
|
2297 |
"Result": 42.44,
|
2298 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2299 |
"Params": 23.6,
|
2300 |
-
"Release": "
|
2301 |
},
|
2302 |
{
|
2303 |
"Model": "Magistral Small 2506",
|
@@ -2307,7 +2307,7 @@
|
|
2307 |
"Result": 37.45,
|
2308 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2309 |
"Params": 23.6,
|
2310 |
-
"Release": "
|
2311 |
},
|
2312 |
{
|
2313 |
"Model": "Magistral Small 2506",
|
@@ -2317,7 +2317,7 @@
|
|
2317 |
"Result": 41.39,
|
2318 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2319 |
"Params": 23.6,
|
2320 |
-
"Release": "
|
2321 |
},
|
2322 |
{
|
2323 |
"Model": "Magistral Small 2506",
|
@@ -2327,7 +2327,7 @@
|
|
2327 |
"Result": 43.36,
|
2328 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2329 |
"Params": 23.6,
|
2330 |
-
"Release": "
|
2331 |
},
|
2332 |
{
|
2333 |
"Model": "Magistral Small 2506",
|
@@ -2337,7 +2337,7 @@
|
|
2337 |
"Result": 40.09,
|
2338 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2339 |
"Params": 23.6,
|
2340 |
-
"Release": "
|
2341 |
},
|
2342 |
{
|
2343 |
"Model": "Magistral Small 2506",
|
@@ -2347,7 +2347,7 @@
|
|
2347 |
"Result": 37.44,
|
2348 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2349 |
"Params": 23.6,
|
2350 |
-
"Release": "
|
2351 |
},
|
2352 |
{
|
2353 |
"Model": "Magistral Small 2506",
|
@@ -2357,7 +2357,7 @@
|
|
2357 |
"Result": 41.39,
|
2358 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2359 |
"Params": 23.6,
|
2360 |
-
"Release": "
|
2361 |
},
|
2362 |
{
|
2363 |
"Model": "Magistral Small 2506",
|
@@ -2367,7 +2367,7 @@
|
|
2367 |
"Result": 40.32,
|
2368 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2369 |
"Params": 23.6,
|
2370 |
-
"Release": "
|
2371 |
},
|
2372 |
{
|
2373 |
"Model": "Magistral Small 2506",
|
@@ -2377,7 +2377,7 @@
|
|
2377 |
"Result": -1.0,
|
2378 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2379 |
"Params": 23.6,
|
2380 |
-
"Release": "
|
2381 |
},
|
2382 |
{
|
2383 |
"Model": "Magistral Small 2506",
|
@@ -2387,7 +2387,7 @@
|
|
2387 |
"Result": 31.28,
|
2388 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2389 |
"Params": 23.6,
|
2390 |
-
"Release": "
|
2391 |
},
|
2392 |
{
|
2393 |
"Model": "Magistral Small 2506",
|
@@ -2397,7 +2397,7 @@
|
|
2397 |
"Result": 68.24,
|
2398 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2399 |
"Params": 23.6,
|
2400 |
-
"Release": "
|
2401 |
},
|
2402 |
{
|
2403 |
"Model": "Magistral Small 2506",
|
@@ -2407,7 +2407,7 @@
|
|
2407 |
"Result": 20.9,
|
2408 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2409 |
"Params": 23.6,
|
2410 |
-
"Release": "
|
2411 |
},
|
2412 |
{
|
2413 |
"Model": "Magistral Small 2506",
|
@@ -2417,7 +2417,7 @@
|
|
2417 |
"Result": 50.59,
|
2418 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2419 |
"Params": 23.6,
|
2420 |
-
"Release": "
|
2421 |
},
|
2422 |
{
|
2423 |
"Model": "Magistral Small 2506",
|
@@ -2427,7 +2427,7 @@
|
|
2427 |
"Result": 20.77,
|
2428 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2429 |
"Params": 23.6,
|
2430 |
-
"Release": "
|
2431 |
},
|
2432 |
{
|
2433 |
"Model": "Magistral Small 2506",
|
@@ -2437,7 +2437,7 @@
|
|
2437 |
"Result": 49.41,
|
2438 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2439 |
"Params": 23.6,
|
2440 |
-
"Release": "
|
2441 |
},
|
2442 |
{
|
2443 |
"Model": "Magistral Small 2506",
|
@@ -2447,7 +2447,7 @@
|
|
2447 |
"Result": 20.11,
|
2448 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2449 |
"Params": 23.6,
|
2450 |
-
"Release": "
|
2451 |
},
|
2452 |
{
|
2453 |
"Model": "Magistral Small 2506",
|
@@ -2457,7 +2457,7 @@
|
|
2457 |
"Result": 41.59,
|
2458 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2459 |
"Params": 23.6,
|
2460 |
-
"Release": "
|
2461 |
},
|
2462 |
{
|
2463 |
"Model": "Magistral Small 2506",
|
@@ -2467,7 +2467,7 @@
|
|
2467 |
"Result": 19.61,
|
2468 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2469 |
"Params": 23.6,
|
2470 |
-
"Release": "
|
2471 |
},
|
2472 |
{
|
2473 |
"Model": "Magistral Small 2506",
|
@@ -2477,7 +2477,7 @@
|
|
2477 |
"Result": 48.97,
|
2478 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2479 |
"Params": 23.6,
|
2480 |
-
"Release": "
|
2481 |
},
|
2482 |
{
|
2483 |
"Model": "Magistral Small 2506",
|
@@ -2487,7 +2487,7 @@
|
|
2487 |
"Result": 20.16,
|
2488 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2489 |
"Params": 23.6,
|
2490 |
-
"Release": "
|
2491 |
},
|
2492 |
{
|
2493 |
"Model": "Magistral Small 2506",
|
@@ -2497,7 +2497,7 @@
|
|
2497 |
"Result": 50.07,
|
2498 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2499 |
"Params": 23.6,
|
2500 |
-
"Release": "
|
2501 |
},
|
2502 |
{
|
2503 |
"Model": "StarChat2 15B v0.1",
|
@@ -7499,4 +7499,4 @@
|
|
7499 |
"Params": 6.74,
|
7500 |
"Release": "V1"
|
7501 |
}
|
7502 |
-
]
|
|
|
507 |
"Result": 96.41,
|
508 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
509 |
"Params": 480,
|
510 |
+
"Release": "V2"
|
511 |
},
|
512 |
{
|
513 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
517 |
"Result": 86.38,
|
518 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
519 |
"Params": 480,
|
520 |
+
"Release": "V2"
|
521 |
},
|
522 |
{
|
523 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
527 |
"Result": 65.38,
|
528 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
529 |
"Params": 480,
|
530 |
+
"Release": "V2"
|
531 |
},
|
532 |
{
|
533 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
537 |
"Result": 59.57,
|
538 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
539 |
"Params": 480,
|
540 |
+
"Release": "V2"
|
541 |
},
|
542 |
{
|
543 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
547 |
"Result": 64.74,
|
548 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
549 |
"Params": 480,
|
550 |
+
"Release": "V2"
|
551 |
},
|
552 |
{
|
553 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
557 |
"Result": 53.62,
|
558 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
559 |
"Params": 480,
|
560 |
+
"Release": "V2"
|
561 |
},
|
562 |
{
|
563 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
567 |
"Result": 64.09,
|
568 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
569 |
"Params": 480,
|
570 |
+
"Release": "V2"
|
571 |
},
|
572 |
{
|
573 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
577 |
"Result": 52.85,
|
578 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
579 |
"Params": 480,
|
580 |
+
"Release": "V2"
|
581 |
},
|
582 |
{
|
583 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
587 |
"Result": 61.91,
|
588 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
589 |
"Params": 480,
|
590 |
+
"Release": "V2"
|
591 |
},
|
592 |
{
|
593 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
597 |
"Result": 53.03,
|
598 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
599 |
"Params": 480,
|
600 |
+
"Release": "V2"
|
601 |
},
|
602 |
{
|
603 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
607 |
"Result": 62.93,
|
608 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
609 |
"Params": 480,
|
610 |
+
"Release": "V2"
|
611 |
},
|
612 |
{
|
613 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
617 |
"Result": 51.81,
|
618 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
619 |
"Params": 480,
|
620 |
+
"Release": "V2"
|
621 |
},
|
622 |
{
|
623 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
627 |
"Result": 38.88,
|
628 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
629 |
"Params": 480,
|
630 |
+
"Release": "V2"
|
631 |
},
|
632 |
{
|
633 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
637 |
"Result": 84.1,
|
638 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
639 |
"Params": 480,
|
640 |
+
"Release": "V2"
|
641 |
},
|
642 |
{
|
643 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
647 |
"Result": 100.0,
|
648 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
649 |
"Params": 480,
|
650 |
+
"Release": "V2"
|
651 |
},
|
652 |
{
|
653 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
657 |
"Result": 58.85,
|
658 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
659 |
"Params": 480,
|
660 |
+
"Release": "V2"
|
661 |
},
|
662 |
{
|
663 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
667 |
"Result": 75.29,
|
668 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
669 |
"Params": 480,
|
670 |
+
"Release": "V2"
|
671 |
},
|
672 |
{
|
673 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
677 |
"Result": 58.46,
|
678 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
679 |
"Params": 480,
|
680 |
+
"Release": "V2"
|
681 |
},
|
682 |
{
|
683 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
687 |
"Result": 75.29,
|
688 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
689 |
"Params": 480,
|
690 |
+
"Release": "V2"
|
691 |
},
|
692 |
{
|
693 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
697 |
"Result": 57.05,
|
698 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
699 |
"Params": 480,
|
700 |
+
"Release": "V2"
|
701 |
},
|
702 |
{
|
703 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
707 |
"Result": 69.63,
|
708 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
709 |
"Params": 480,
|
710 |
+
"Release": "V2"
|
711 |
},
|
712 |
{
|
713 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
717 |
"Result": 55.54,
|
718 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
719 |
"Params": 480,
|
720 |
+
"Release": "V2"
|
721 |
},
|
722 |
{
|
723 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
727 |
"Result": 73.95,
|
728 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
729 |
"Params": 480,
|
730 |
+
"Release": "V2"
|
731 |
},
|
732 |
{
|
733 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
737 |
"Result": 55.79,
|
738 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
739 |
"Params": 480,
|
740 |
+
"Release": "V2"
|
741 |
},
|
742 |
{
|
743 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
747 |
"Result": 76.76,
|
748 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
749 |
"Params": 480,
|
750 |
+
"Release": "V2"
|
751 |
},
|
752 |
{
|
753 |
"Model": "Llama 3.1 405B",
|
|
|
2277 |
"Result": 42.95,
|
2278 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2279 |
"Params": 23.6,
|
2280 |
+
"Release": "V2"
|
2281 |
},
|
2282 |
{
|
2283 |
"Model": "Magistral Small 2506",
|
|
|
2287 |
"Result": 43.4,
|
2288 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2289 |
"Params": 23.6,
|
2290 |
+
"Release": "V2"
|
2291 |
},
|
2292 |
{
|
2293 |
"Model": "Magistral Small 2506",
|
|
|
2297 |
"Result": 42.44,
|
2298 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2299 |
"Params": 23.6,
|
2300 |
+
"Release": "V2"
|
2301 |
},
|
2302 |
{
|
2303 |
"Model": "Magistral Small 2506",
|
|
|
2307 |
"Result": 37.45,
|
2308 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2309 |
"Params": 23.6,
|
2310 |
+
"Release": "V2"
|
2311 |
},
|
2312 |
{
|
2313 |
"Model": "Magistral Small 2506",
|
|
|
2317 |
"Result": 41.39,
|
2318 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2319 |
"Params": 23.6,
|
2320 |
+
"Release": "V2"
|
2321 |
},
|
2322 |
{
|
2323 |
"Model": "Magistral Small 2506",
|
|
|
2327 |
"Result": 43.36,
|
2328 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2329 |
"Params": 23.6,
|
2330 |
+
"Release": "V2"
|
2331 |
},
|
2332 |
{
|
2333 |
"Model": "Magistral Small 2506",
|
|
|
2337 |
"Result": 40.09,
|
2338 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2339 |
"Params": 23.6,
|
2340 |
+
"Release": "V2"
|
2341 |
},
|
2342 |
{
|
2343 |
"Model": "Magistral Small 2506",
|
|
|
2347 |
"Result": 37.44,
|
2348 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2349 |
"Params": 23.6,
|
2350 |
+
"Release": "V2"
|
2351 |
},
|
2352 |
{
|
2353 |
"Model": "Magistral Small 2506",
|
|
|
2357 |
"Result": 41.39,
|
2358 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2359 |
"Params": 23.6,
|
2360 |
+
"Release": "V2"
|
2361 |
},
|
2362 |
{
|
2363 |
"Model": "Magistral Small 2506",
|
|
|
2367 |
"Result": 40.32,
|
2368 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2369 |
"Params": 23.6,
|
2370 |
+
"Release": "V2"
|
2371 |
},
|
2372 |
{
|
2373 |
"Model": "Magistral Small 2506",
|
|
|
2377 |
"Result": -1.0,
|
2378 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2379 |
"Params": 23.6,
|
2380 |
+
"Release": "V2"
|
2381 |
},
|
2382 |
{
|
2383 |
"Model": "Magistral Small 2506",
|
|
|
2387 |
"Result": 31.28,
|
2388 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2389 |
"Params": 23.6,
|
2390 |
+
"Release": "V2"
|
2391 |
},
|
2392 |
{
|
2393 |
"Model": "Magistral Small 2506",
|
|
|
2397 |
"Result": 68.24,
|
2398 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2399 |
"Params": 23.6,
|
2400 |
+
"Release": "V2"
|
2401 |
},
|
2402 |
{
|
2403 |
"Model": "Magistral Small 2506",
|
|
|
2407 |
"Result": 20.9,
|
2408 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2409 |
"Params": 23.6,
|
2410 |
+
"Release": "V2"
|
2411 |
},
|
2412 |
{
|
2413 |
"Model": "Magistral Small 2506",
|
|
|
2417 |
"Result": 50.59,
|
2418 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2419 |
"Params": 23.6,
|
2420 |
+
"Release": "V2"
|
2421 |
},
|
2422 |
{
|
2423 |
"Model": "Magistral Small 2506",
|
|
|
2427 |
"Result": 20.77,
|
2428 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2429 |
"Params": 23.6,
|
2430 |
+
"Release": "V2"
|
2431 |
},
|
2432 |
{
|
2433 |
"Model": "Magistral Small 2506",
|
|
|
2437 |
"Result": 49.41,
|
2438 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2439 |
"Params": 23.6,
|
2440 |
+
"Release": "V2"
|
2441 |
},
|
2442 |
{
|
2443 |
"Model": "Magistral Small 2506",
|
|
|
2447 |
"Result": 20.11,
|
2448 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2449 |
"Params": 23.6,
|
2450 |
+
"Release": "V2"
|
2451 |
},
|
2452 |
{
|
2453 |
"Model": "Magistral Small 2506",
|
|
|
2457 |
"Result": 41.59,
|
2458 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2459 |
"Params": 23.6,
|
2460 |
+
"Release": "V2"
|
2461 |
},
|
2462 |
{
|
2463 |
"Model": "Magistral Small 2506",
|
|
|
2467 |
"Result": 19.61,
|
2468 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2469 |
"Params": 23.6,
|
2470 |
+
"Release": "V2"
|
2471 |
},
|
2472 |
{
|
2473 |
"Model": "Magistral Small 2506",
|
|
|
2477 |
"Result": 48.97,
|
2478 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2479 |
"Params": 23.6,
|
2480 |
+
"Release": "V2"
|
2481 |
},
|
2482 |
{
|
2483 |
"Model": "Magistral Small 2506",
|
|
|
2487 |
"Result": 20.16,
|
2488 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2489 |
"Params": 23.6,
|
2490 |
+
"Release": "V2"
|
2491 |
},
|
2492 |
{
|
2493 |
"Model": "Magistral Small 2506",
|
|
|
2497 |
"Result": 50.07,
|
2498 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2499 |
"Params": 23.6,
|
2500 |
+
"Release": "V2"
|
2501 |
},
|
2502 |
{
|
2503 |
"Model": "StarChat2 15B v0.1",
|
|
|
7499 |
"Params": 6.74,
|
7500 |
"Release": "V1"
|
7501 |
}
|
7502 |
+
]
|
results/results_verilator.json
CHANGED
@@ -507,7 +507,7 @@
|
|
507 |
"Result": 95.9,
|
508 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
509 |
"Params": 480,
|
510 |
-
"Release": "
|
511 |
},
|
512 |
{
|
513 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -517,7 +517,7 @@
|
|
517 |
"Result": 89.36,
|
518 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
519 |
"Params": 480,
|
520 |
-
"Release": "
|
521 |
},
|
522 |
{
|
523 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -527,7 +527,7 @@
|
|
527 |
"Result": 66.03,
|
528 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
529 |
"Params": 480,
|
530 |
-
"Release": "
|
531 |
},
|
532 |
{
|
533 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -537,7 +537,7 @@
|
|
537 |
"Result": 61.28,
|
538 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
539 |
"Params": 480,
|
540 |
-
"Release": "
|
541 |
},
|
542 |
{
|
543 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -547,7 +547,7 @@
|
|
547 |
"Result": 65.26,
|
548 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
549 |
"Params": 480,
|
550 |
-
"Release": "
|
551 |
},
|
552 |
{
|
553 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -557,7 +557,7 @@
|
|
557 |
"Result": 54.04,
|
558 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
559 |
"Params": 480,
|
560 |
-
"Release": "
|
561 |
},
|
562 |
{
|
563 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -567,7 +567,7 @@
|
|
567 |
"Result": 65.33,
|
568 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
569 |
"Params": 480,
|
570 |
-
"Release": "
|
571 |
},
|
572 |
{
|
573 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -577,7 +577,7 @@
|
|
577 |
"Result": 53.43,
|
578 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
579 |
"Params": 480,
|
580 |
-
"Release": "
|
581 |
},
|
582 |
{
|
583 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -587,7 +587,7 @@
|
|
587 |
"Result": 62.45,
|
588 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
589 |
"Params": 480,
|
590 |
-
"Release": "
|
591 |
},
|
592 |
{
|
593 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -597,7 +597,7 @@
|
|
597 |
"Result": 53.43,
|
598 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
599 |
"Params": 480,
|
600 |
-
"Release": "
|
601 |
},
|
602 |
{
|
603 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -607,7 +607,7 @@
|
|
607 |
"Result": 64.24,
|
608 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
609 |
"Params": 480,
|
610 |
-
"Release": "
|
611 |
},
|
612 |
{
|
613 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -617,7 +617,7 @@
|
|
617 |
"Result": 52.26,
|
618 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
619 |
"Params": 480,
|
620 |
-
"Release": "
|
621 |
},
|
622 |
{
|
623 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -627,7 +627,7 @@
|
|
627 |
"Result": 38.88,
|
628 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
629 |
"Params": 480,
|
630 |
-
"Release": "
|
631 |
},
|
632 |
{
|
633 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -637,7 +637,7 @@
|
|
637 |
"Result": 83.97,
|
638 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
639 |
"Params": 480,
|
640 |
-
"Release": "
|
641 |
},
|
642 |
{
|
643 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -647,7 +647,7 @@
|
|
647 |
"Result": 100.0,
|
648 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
649 |
"Params": 480,
|
650 |
-
"Release": "
|
651 |
},
|
652 |
{
|
653 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -657,7 +657,7 @@
|
|
657 |
"Result": 58.72,
|
658 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
659 |
"Params": 480,
|
660 |
-
"Release": "
|
661 |
},
|
662 |
{
|
663 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -667,7 +667,7 @@
|
|
667 |
"Result": 75.29,
|
668 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
669 |
"Params": 480,
|
670 |
-
"Release": "
|
671 |
},
|
672 |
{
|
673 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -677,7 +677,7 @@
|
|
677 |
"Result": 58.21,
|
678 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
679 |
"Params": 480,
|
680 |
-
"Release": "
|
681 |
},
|
682 |
{
|
683 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -687,7 +687,7 @@
|
|
687 |
"Result": 75.29,
|
688 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
689 |
"Params": 480,
|
690 |
-
"Release": "
|
691 |
},
|
692 |
{
|
693 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -697,7 +697,7 @@
|
|
697 |
"Result": 57.58,
|
698 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
699 |
"Params": 480,
|
700 |
-
"Release": "
|
701 |
},
|
702 |
{
|
703 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -707,7 +707,7 @@
|
|
707 |
"Result": 69.63,
|
708 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
709 |
"Params": 480,
|
710 |
-
"Release": "
|
711 |
},
|
712 |
{
|
713 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -717,7 +717,7 @@
|
|
717 |
"Result": 55.42,
|
718 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
719 |
"Params": 480,
|
720 |
-
"Release": "
|
721 |
},
|
722 |
{
|
723 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -727,7 +727,7 @@
|
|
727 |
"Result": 73.95,
|
728 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
729 |
"Params": 480,
|
730 |
-
"Release": "
|
731 |
},
|
732 |
{
|
733 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -737,7 +737,7 @@
|
|
737 |
"Result": 56.5,
|
738 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
739 |
"Params": 480,
|
740 |
-
"Release": "
|
741 |
},
|
742 |
{
|
743 |
"Model": "Qwen3 Coder 480B A35B",
|
@@ -747,7 +747,7 @@
|
|
747 |
"Result": 76.76,
|
748 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
749 |
"Params": 480,
|
750 |
-
"Release": "
|
751 |
},
|
752 |
{
|
753 |
"Model": "Llama 3.1 405B",
|
@@ -2257,7 +2257,7 @@
|
|
2257 |
"Result": 65.13,
|
2258 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2259 |
"Params": 23.6,
|
2260 |
-
"Release": "
|
2261 |
},
|
2262 |
{
|
2263 |
"Model": "Magistral Small 2506",
|
@@ -2267,7 +2267,7 @@
|
|
2267 |
"Result": 74.04,
|
2268 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2269 |
"Params": 23.6,
|
2270 |
-
"Release": "
|
2271 |
},
|
2272 |
{
|
2273 |
"Model": "Magistral Small 2506",
|
@@ -2277,7 +2277,7 @@
|
|
2277 |
"Result": 42.95,
|
2278 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2279 |
"Params": 23.6,
|
2280 |
-
"Release": "
|
2281 |
},
|
2282 |
{
|
2283 |
"Model": "Magistral Small 2506",
|
@@ -2287,7 +2287,7 @@
|
|
2287 |
"Result": 44.26,
|
2288 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2289 |
"Params": 23.6,
|
2290 |
-
"Release": "
|
2291 |
},
|
2292 |
{
|
2293 |
"Model": "Magistral Small 2506",
|
@@ -2297,7 +2297,7 @@
|
|
2297 |
"Result": 42.31,
|
2298 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2299 |
"Params": 23.6,
|
2300 |
-
"Release": "
|
2301 |
},
|
2302 |
{
|
2303 |
"Model": "Magistral Small 2506",
|
@@ -2307,7 +2307,7 @@
|
|
2307 |
"Result": 37.45,
|
2308 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2309 |
"Params": 23.6,
|
2310 |
-
"Release": "
|
2311 |
},
|
2312 |
{
|
2313 |
"Model": "Magistral Small 2506",
|
@@ -2317,7 +2317,7 @@
|
|
2317 |
"Result": 41.81,
|
2318 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2319 |
"Params": 23.6,
|
2320 |
-
"Release": "
|
2321 |
},
|
2322 |
{
|
2323 |
"Model": "Magistral Small 2506",
|
@@ -2327,7 +2327,7 @@
|
|
2327 |
"Result": 43.1,
|
2328 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2329 |
"Params": 23.6,
|
2330 |
-
"Release": "
|
2331 |
},
|
2332 |
{
|
2333 |
"Model": "Magistral Small 2506",
|
@@ -2337,7 +2337,7 @@
|
|
2337 |
"Result": 40.19,
|
2338 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2339 |
"Params": 23.6,
|
2340 |
-
"Release": "
|
2341 |
},
|
2342 |
{
|
2343 |
"Model": "Magistral Small 2506",
|
@@ -2347,7 +2347,7 @@
|
|
2347 |
"Result": 37.37,
|
2348 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2349 |
"Params": 23.6,
|
2350 |
-
"Release": "
|
2351 |
},
|
2352 |
{
|
2353 |
"Model": "Magistral Small 2506",
|
@@ -2357,7 +2357,7 @@
|
|
2357 |
"Result": 41.75,
|
2358 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2359 |
"Params": 23.6,
|
2360 |
-
"Release": "
|
2361 |
},
|
2362 |
{
|
2363 |
"Model": "Magistral Small 2506",
|
@@ -2367,7 +2367,7 @@
|
|
2367 |
"Result": 40.35,
|
2368 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2369 |
"Params": 23.6,
|
2370 |
-
"Release": "
|
2371 |
},
|
2372 |
{
|
2373 |
"Model": "Magistral Small 2506",
|
@@ -2377,7 +2377,7 @@
|
|
2377 |
"Result": -1.0,
|
2378 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2379 |
"Params": 23.6,
|
2380 |
-
"Release": "
|
2381 |
},
|
2382 |
{
|
2383 |
"Model": "Magistral Small 2506",
|
@@ -2387,7 +2387,7 @@
|
|
2387 |
"Result": 31.79,
|
2388 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2389 |
"Params": 23.6,
|
2390 |
-
"Release": "
|
2391 |
},
|
2392 |
{
|
2393 |
"Model": "Magistral Small 2506",
|
@@ -2397,7 +2397,7 @@
|
|
2397 |
"Result": 70.59,
|
2398 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2399 |
"Params": 23.6,
|
2400 |
-
"Release": "
|
2401 |
},
|
2402 |
{
|
2403 |
"Model": "Magistral Small 2506",
|
@@ -2407,7 +2407,7 @@
|
|
2407 |
"Result": 21.03,
|
2408 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2409 |
"Params": 23.6,
|
2410 |
-
"Release": "
|
2411 |
},
|
2412 |
{
|
2413 |
"Model": "Magistral Small 2506",
|
@@ -2417,7 +2417,7 @@
|
|
2417 |
"Result": 55.29,
|
2418 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2419 |
"Params": 23.6,
|
2420 |
-
"Release": "
|
2421 |
},
|
2422 |
{
|
2423 |
"Model": "Magistral Small 2506",
|
@@ -2427,7 +2427,7 @@
|
|
2427 |
"Result": 20.77,
|
2428 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2429 |
"Params": 23.6,
|
2430 |
-
"Release": "
|
2431 |
},
|
2432 |
{
|
2433 |
"Model": "Magistral Small 2506",
|
@@ -2437,7 +2437,7 @@
|
|
2437 |
"Result": 54.12,
|
2438 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2439 |
"Params": 23.6,
|
2440 |
-
"Release": "
|
2441 |
},
|
2442 |
{
|
2443 |
"Model": "Magistral Small 2506",
|
@@ -2447,7 +2447,7 @@
|
|
2447 |
"Result": 20.33,
|
2448 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2449 |
"Params": 23.6,
|
2450 |
-
"Release": "
|
2451 |
},
|
2452 |
{
|
2453 |
"Model": "Magistral Small 2506",
|
@@ -2457,7 +2457,7 @@
|
|
2457 |
"Result": 46.6,
|
2458 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2459 |
"Params": 23.6,
|
2460 |
-
"Release": "
|
2461 |
},
|
2462 |
{
|
2463 |
"Model": "Magistral Small 2506",
|
@@ -2467,7 +2467,7 @@
|
|
2467 |
"Result": 20.08,
|
2468 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2469 |
"Params": 23.6,
|
2470 |
-
"Release": "
|
2471 |
},
|
2472 |
{
|
2473 |
"Model": "Magistral Small 2506",
|
@@ -2477,7 +2477,7 @@
|
|
2477 |
"Result": 54.02,
|
2478 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2479 |
"Params": 23.6,
|
2480 |
-
"Release": "
|
2481 |
},
|
2482 |
{
|
2483 |
"Model": "Magistral Small 2506",
|
@@ -2487,7 +2487,7 @@
|
|
2487 |
"Result": 20.66,
|
2488 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2489 |
"Params": 23.6,
|
2490 |
-
"Release": "
|
2491 |
},
|
2492 |
{
|
2493 |
"Model": "Magistral Small 2506",
|
@@ -2497,7 +2497,7 @@
|
|
2497 |
"Result": 55.06,
|
2498 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2499 |
"Params": 23.6,
|
2500 |
-
"Release": "
|
2501 |
},
|
2502 |
{
|
2503 |
"Model": "StarChat2 15B v0.1",
|
|
|
507 |
"Result": 95.9,
|
508 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
509 |
"Params": 480,
|
510 |
+
"Release": "V2"
|
511 |
},
|
512 |
{
|
513 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
517 |
"Result": 89.36,
|
518 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
519 |
"Params": 480,
|
520 |
+
"Release": "V2"
|
521 |
},
|
522 |
{
|
523 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
527 |
"Result": 66.03,
|
528 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
529 |
"Params": 480,
|
530 |
+
"Release": "V2"
|
531 |
},
|
532 |
{
|
533 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
537 |
"Result": 61.28,
|
538 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
539 |
"Params": 480,
|
540 |
+
"Release": "V2"
|
541 |
},
|
542 |
{
|
543 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
547 |
"Result": 65.26,
|
548 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
549 |
"Params": 480,
|
550 |
+
"Release": "V2"
|
551 |
},
|
552 |
{
|
553 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
557 |
"Result": 54.04,
|
558 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
559 |
"Params": 480,
|
560 |
+
"Release": "V2"
|
561 |
},
|
562 |
{
|
563 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
567 |
"Result": 65.33,
|
568 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
569 |
"Params": 480,
|
570 |
+
"Release": "V2"
|
571 |
},
|
572 |
{
|
573 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
577 |
"Result": 53.43,
|
578 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
579 |
"Params": 480,
|
580 |
+
"Release": "V2"
|
581 |
},
|
582 |
{
|
583 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
587 |
"Result": 62.45,
|
588 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
589 |
"Params": 480,
|
590 |
+
"Release": "V2"
|
591 |
},
|
592 |
{
|
593 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
597 |
"Result": 53.43,
|
598 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
599 |
"Params": 480,
|
600 |
+
"Release": "V2"
|
601 |
},
|
602 |
{
|
603 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
607 |
"Result": 64.24,
|
608 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
609 |
"Params": 480,
|
610 |
+
"Release": "V2"
|
611 |
},
|
612 |
{
|
613 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
617 |
"Result": 52.26,
|
618 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
619 |
"Params": 480,
|
620 |
+
"Release": "V2"
|
621 |
},
|
622 |
{
|
623 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
627 |
"Result": 38.88,
|
628 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
629 |
"Params": 480,
|
630 |
+
"Release": "V2"
|
631 |
},
|
632 |
{
|
633 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
637 |
"Result": 83.97,
|
638 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
639 |
"Params": 480,
|
640 |
+
"Release": "V2"
|
641 |
},
|
642 |
{
|
643 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
647 |
"Result": 100.0,
|
648 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
649 |
"Params": 480,
|
650 |
+
"Release": "V2"
|
651 |
},
|
652 |
{
|
653 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
657 |
"Result": 58.72,
|
658 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
659 |
"Params": 480,
|
660 |
+
"Release": "V2"
|
661 |
},
|
662 |
{
|
663 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
667 |
"Result": 75.29,
|
668 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
669 |
"Params": 480,
|
670 |
+
"Release": "V2"
|
671 |
},
|
672 |
{
|
673 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
677 |
"Result": 58.21,
|
678 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
679 |
"Params": 480,
|
680 |
+
"Release": "V2"
|
681 |
},
|
682 |
{
|
683 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
687 |
"Result": 75.29,
|
688 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
689 |
"Params": 480,
|
690 |
+
"Release": "V2"
|
691 |
},
|
692 |
{
|
693 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
697 |
"Result": 57.58,
|
698 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
699 |
"Params": 480,
|
700 |
+
"Release": "V2"
|
701 |
},
|
702 |
{
|
703 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
707 |
"Result": 69.63,
|
708 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
709 |
"Params": 480,
|
710 |
+
"Release": "V2"
|
711 |
},
|
712 |
{
|
713 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
717 |
"Result": 55.42,
|
718 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
719 |
"Params": 480,
|
720 |
+
"Release": "V2"
|
721 |
},
|
722 |
{
|
723 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
727 |
"Result": 73.95,
|
728 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
729 |
"Params": 480,
|
730 |
+
"Release": "V2"
|
731 |
},
|
732 |
{
|
733 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
737 |
"Result": 56.5,
|
738 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
739 |
"Params": 480,
|
740 |
+
"Release": "V2"
|
741 |
},
|
742 |
{
|
743 |
"Model": "Qwen3 Coder 480B A35B",
|
|
|
747 |
"Result": 76.76,
|
748 |
"Model URL": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
749 |
"Params": 480,
|
750 |
+
"Release": "V2"
|
751 |
},
|
752 |
{
|
753 |
"Model": "Llama 3.1 405B",
|
|
|
2257 |
"Result": 65.13,
|
2258 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2259 |
"Params": 23.6,
|
2260 |
+
"Release": "V2"
|
2261 |
},
|
2262 |
{
|
2263 |
"Model": "Magistral Small 2506",
|
|
|
2267 |
"Result": 74.04,
|
2268 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2269 |
"Params": 23.6,
|
2270 |
+
"Release": "V2"
|
2271 |
},
|
2272 |
{
|
2273 |
"Model": "Magistral Small 2506",
|
|
|
2277 |
"Result": 42.95,
|
2278 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2279 |
"Params": 23.6,
|
2280 |
+
"Release": "V2"
|
2281 |
},
|
2282 |
{
|
2283 |
"Model": "Magistral Small 2506",
|
|
|
2287 |
"Result": 44.26,
|
2288 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2289 |
"Params": 23.6,
|
2290 |
+
"Release": "V2"
|
2291 |
},
|
2292 |
{
|
2293 |
"Model": "Magistral Small 2506",
|
|
|
2297 |
"Result": 42.31,
|
2298 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2299 |
"Params": 23.6,
|
2300 |
+
"Release": "V2"
|
2301 |
},
|
2302 |
{
|
2303 |
"Model": "Magistral Small 2506",
|
|
|
2307 |
"Result": 37.45,
|
2308 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2309 |
"Params": 23.6,
|
2310 |
+
"Release": "V2"
|
2311 |
},
|
2312 |
{
|
2313 |
"Model": "Magistral Small 2506",
|
|
|
2317 |
"Result": 41.81,
|
2318 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2319 |
"Params": 23.6,
|
2320 |
+
"Release": "V2"
|
2321 |
},
|
2322 |
{
|
2323 |
"Model": "Magistral Small 2506",
|
|
|
2327 |
"Result": 43.1,
|
2328 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2329 |
"Params": 23.6,
|
2330 |
+
"Release": "V2"
|
2331 |
},
|
2332 |
{
|
2333 |
"Model": "Magistral Small 2506",
|
|
|
2337 |
"Result": 40.19,
|
2338 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2339 |
"Params": 23.6,
|
2340 |
+
"Release": "V2"
|
2341 |
},
|
2342 |
{
|
2343 |
"Model": "Magistral Small 2506",
|
|
|
2347 |
"Result": 37.37,
|
2348 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2349 |
"Params": 23.6,
|
2350 |
+
"Release": "V2"
|
2351 |
},
|
2352 |
{
|
2353 |
"Model": "Magistral Small 2506",
|
|
|
2357 |
"Result": 41.75,
|
2358 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2359 |
"Params": 23.6,
|
2360 |
+
"Release": "V2"
|
2361 |
},
|
2362 |
{
|
2363 |
"Model": "Magistral Small 2506",
|
|
|
2367 |
"Result": 40.35,
|
2368 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2369 |
"Params": 23.6,
|
2370 |
+
"Release": "V2"
|
2371 |
},
|
2372 |
{
|
2373 |
"Model": "Magistral Small 2506",
|
|
|
2377 |
"Result": -1.0,
|
2378 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2379 |
"Params": 23.6,
|
2380 |
+
"Release": "V2"
|
2381 |
},
|
2382 |
{
|
2383 |
"Model": "Magistral Small 2506",
|
|
|
2387 |
"Result": 31.79,
|
2388 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2389 |
"Params": 23.6,
|
2390 |
+
"Release": "V2"
|
2391 |
},
|
2392 |
{
|
2393 |
"Model": "Magistral Small 2506",
|
|
|
2397 |
"Result": 70.59,
|
2398 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2399 |
"Params": 23.6,
|
2400 |
+
"Release": "V2"
|
2401 |
},
|
2402 |
{
|
2403 |
"Model": "Magistral Small 2506",
|
|
|
2407 |
"Result": 21.03,
|
2408 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2409 |
"Params": 23.6,
|
2410 |
+
"Release": "V2"
|
2411 |
},
|
2412 |
{
|
2413 |
"Model": "Magistral Small 2506",
|
|
|
2417 |
"Result": 55.29,
|
2418 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2419 |
"Params": 23.6,
|
2420 |
+
"Release": "V2"
|
2421 |
},
|
2422 |
{
|
2423 |
"Model": "Magistral Small 2506",
|
|
|
2427 |
"Result": 20.77,
|
2428 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2429 |
"Params": 23.6,
|
2430 |
+
"Release": "V2"
|
2431 |
},
|
2432 |
{
|
2433 |
"Model": "Magistral Small 2506",
|
|
|
2437 |
"Result": 54.12,
|
2438 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2439 |
"Params": 23.6,
|
2440 |
+
"Release": "V2"
|
2441 |
},
|
2442 |
{
|
2443 |
"Model": "Magistral Small 2506",
|
|
|
2447 |
"Result": 20.33,
|
2448 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2449 |
"Params": 23.6,
|
2450 |
+
"Release": "V2"
|
2451 |
},
|
2452 |
{
|
2453 |
"Model": "Magistral Small 2506",
|
|
|
2457 |
"Result": 46.6,
|
2458 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2459 |
"Params": 23.6,
|
2460 |
+
"Release": "V2"
|
2461 |
},
|
2462 |
{
|
2463 |
"Model": "Magistral Small 2506",
|
|
|
2467 |
"Result": 20.08,
|
2468 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2469 |
"Params": 23.6,
|
2470 |
+
"Release": "V2"
|
2471 |
},
|
2472 |
{
|
2473 |
"Model": "Magistral Small 2506",
|
|
|
2477 |
"Result": 54.02,
|
2478 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2479 |
"Params": 23.6,
|
2480 |
+
"Release": "V2"
|
2481 |
},
|
2482 |
{
|
2483 |
"Model": "Magistral Small 2506",
|
|
|
2487 |
"Result": 20.66,
|
2488 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2489 |
"Params": 23.6,
|
2490 |
+
"Release": "V2"
|
2491 |
},
|
2492 |
{
|
2493 |
"Model": "Magistral Small 2506",
|
|
|
2497 |
"Result": 55.06,
|
2498 |
"Model URL": "https://huggingface.co/mistralai/Magistral-Small-2506",
|
2499 |
"Params": 23.6,
|
2500 |
+
"Release": "V2"
|
2501 |
},
|
2502 |
{
|
2503 |
"Model": "StarChat2 15B v0.1",
|