Skip to content

Commit ca9b588

Browse files
DVampireDVampire
committed
update index
1 parent 0d05cc2 commit ca9b588

File tree

1 file changed

+116
-5
lines changed

1 file changed

+116
-5
lines changed

‎docs/index.html‎

Lines changed: 116 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -374,24 +374,135 @@ <h2 class="text-3xl font-bold text-gray-900 mb-4">3. Experiments</h2>
374374
<div class="w-24 h-1 bg-primary-600 mx-auto"></div>
375375
</div>
376376

377-
<!-- Benchmarks -->
377+
<!-- GAIA Benchmark Chart -->
378+
<div class="mb-16">
379+
<h3 class="text-2xl font-semibold text-gray-900 mb-8 text-center">GAIA Benchmark Test Results</h3>
380+
<div class="bg-white p-8 rounded-xl shadow-sm">
381+
<div class="flex items-center justify-between mb-6">
382+
<div class="flex items-center space-x-4">
383+
<div class="flex items-center space-x-2">
384+
<div class="w-4 h-4 bg-gradient-to-r from-blue-400 to-cyan-400 rounded"></div>
385+
<span class="text-sm text-gray-600">Skywork Deep Research Agent (Our)</span>
386+
</div>
387+
<div class="flex items-center space-x-2">
388+
<div class="w-4 h-4 bg-gray-400 rounded"></div>
389+
<span class="text-sm text-gray-600">Other Models</span>
390+
</div>
391+
</div>
392+
</div>
393+
394+
<div class="space-y-4">
395+
<!-- Skywork DRA -->
396+
<div class="flex items-center">
397+
<div class="w-48 text-sm text-gray-600">Skywork DRA</div>
398+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
399+
<div class="bg-gradient-to-r from-blue-400 to-cyan-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 97.6%">
400+
<span class="text-white font-semibold text-sm">83.06</span>
401+
</div>
402+
</div>
403+
</div>
404+
405+
<!-- Skywork DRA (w/o MCP) -->
406+
<div class="flex items-center">
407+
<div class="w-48 text-sm text-gray-600">Skywork DRA (w/o MCP)</div>
408+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
409+
<div class="bg-gradient-to-r from-blue-400 to-cyan-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 93.0%">
410+
<span class="text-white font-semibold text-sm">79.07</span>
411+
</div>
412+
</div>
413+
</div>
414+
415+
<!-- Aworld -->
416+
<div class="flex items-center">
417+
<div class="w-48 text-sm text-gray-600">Aworld</div>
418+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
419+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 96.1%">
420+
<span class="text-white font-semibold text-sm">81.73</span>
421+
</div>
422+
</div>
423+
</div>
424+
425+
<!-- Su Zero Ultra -->
426+
<div class="flex items-center">
427+
<div class="w-48 text-sm text-gray-600">Su Zero Ultra</div>
428+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
429+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 94.6%">
430+
<span class="text-white font-semibold text-sm">80.40</span>
431+
</div>
432+
</div>
433+
</div>
434+
435+
<!-- h2oGPTe Agent -->
436+
<div class="flex items-center">
437+
<div class="w-48 text-sm text-gray-600">h2oGPTe Agent</div>
438+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
439+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 93.8%">
440+
<span class="text-white font-semibold text-sm">79.73</span>
441+
</div>
442+
</div>
443+
</div>
444+
445+
<!-- desearch -->
446+
<div class="flex items-center">
447+
<div class="w-48 text-sm text-gray-600">desearch</div>
448+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
449+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 91.8%">
450+
<span class="text-white font-semibold text-sm">78.07</span>
451+
</div>
452+
</div>
453+
</div>
454+
455+
<!-- Alita -->
456+
<div class="flex items-center">
457+
<div class="w-48 text-sm text-gray-600">Alita</div>
458+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
459+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 88.7%">
460+
<span class="text-white font-semibold text-sm">75.42</span>
461+
</div>
462+
</div>
463+
</div>
464+
465+
<!-- Langfun Agent -->
466+
<div class="flex items-center">
467+
<div class="w-48 text-sm text-gray-600">Langfun Agent</div>
468+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
469+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 85.9%">
470+
<span class="text-white font-semibold text-sm">73.09</span>
471+
</div>
472+
</div>
473+
</div>
474+
475+
<!-- JoyAgent-Genie -->
476+
<div class="flex items-center">
477+
<div class="w-48 text-sm text-gray-600">JoyAgent-Genie</div>
478+
<div class="flex-1 bg-gray-200 rounded-full h-8 relative">
479+
<div class="bg-gray-400 h-8 rounded-full flex items-center justify-end pr-3" style="width: 76.6%">
480+
<span class="text-white font-semibold text-sm">65.12</span>
481+
</div>
482+
</div>
483+
</div>
484+
</div>
485+
</div>
486+
</div>
487+
488+
<!-- Benchmark Summary -->
378489
<div class="grid lg:grid-cols-3 gap-8 mb-16">
379490
<div class="bg-gradient-to-br from-green-50 to-emerald-50 p-6 rounded-xl">
380491
<h3 class="text-xl font-semibold text-gray-900 mb-3">SimpleQA Benchmark</h3>
381492
<p class="text-gray-600 mb-4">Evaluation on simple question-answering tasks to assess basic reasoning capabilities.</p>
382-
<div class="text-2xl font-bold text-green-600">High Performance</div>
493+
<div class="text-2xl font-bold text-green-600">95.3</div>
383494
</div>
384495

385496
<div class="bg-gradient-to-br from-blue-50 to-cyan-50 p-6 rounded-xl">
386-
<h3 class="text-xl font-semibold text-gray-900 mb-3">GAIA Benchmark</h3>
497+
<h3 class="text-xl font-semibold text-gray-900 mb-3">GAIA Benchmark Validation</h3>
387498
<p class="text-gray-600 mb-4">Comprehensive evaluation on real-world tasks requiring web search and reasoning.</p>
388-
<div class="text-2xl font-bold text-blue-600">79.07 Average</div>
499+
<div class="text-2xl font-bold text-blue-600">82.42</div>
389500
</div>
390501

391502
<div class="bg-gradient-to-br from-purple-50 to-violet-50 p-6 rounded-xl">
392503
<h3 class="text-xl font-semibold text-gray-900 mb-3">HLE Benchmark</h3>
393504
<p class="text-gray-600 mb-4">Human-level evaluation benchmark for complex reasoning and planning tasks.</p>
394-
<div class="text-2xl font-bold text-purple-600">State-of-the-Art</div>
505+
<div class="text-2xl font-bold text-purple-600">25.9</div>
395506
</div>
396507
</div>
397508

0 commit comments

Comments
 (0)