TechDaily 科技早报

2026-08-08 · AI / 互联网 / 科技公司每日动态

今日 68 条新闻来自 8 个来源
实时资讯 →

模型能力排行 更新于 2026-08-08

综合能力 · AA 智能指数 — Artificial Analysis 智能指数(经 DataLearner 聚合) · 数据更新 2026-08-02 · 指标:智能指数 0-100

#模型机构分数
1Claude Opus 5 (max)Anthropic61
2Claude Opus 5 (xhigh)Anthropic60
3Claude Fable 5Anthropic60
4GPT-5.6 Sol (max)OpenAI59
5Claude Opus 5 (high)Anthropic59
6GPT-5.6 Sol (xhigh)OpenAI58
7Kimi K3 (max)Kimi57
8Claude Opus 5 (medium)Anthropic56
9GPT-5.6 Sol (high)OpenAI56
10GPT-5.6 Terra (max)OpenAI55

对话体验 · LMArena 盲测 — LMArena 匿名人类盲测(经 DataLearner 聚合) · 数据更新 2026-08-01 · 指标:Elo 评分

#模型机构分数
1Claude Fable 5Anthropic1509
2Claude Opus 4.6 (thinking)Anthropic1505
3Opus 4.7 (thinking)Anthropic1502
4Claude Opus 4.6Anthropic1497
5Opus 4.7Anthropic1492
6claude-opus-5-highAnthropic1492
7claude-opus-5-maxAnthropic1490
8F Muse Spark 1.1Facebook AI研究实验室1490
9F Muse SparkFacebook AI研究实验室1488
10Gemini 3 ProGoogle Deep Mind1486

代码能力 · SWE-bench Verified — SWE-bench 官方(swebench.com),真实 GitHub issue 工程任务 · 数据更新 官方持续更新 · 指标:500 题解决率 %

#模型机构分数
1live-SWE-agent + Claude 4.5 Opus medium (20251101)79.2%
2Sonar Foundation Agent + Claude 4.5 Opus79.2%
3TRAE + Doubao-Seed-Code78.8%
4live-SWE-agent + Gemini 3 Pro Preview (2025-11-18)77.4%
5Atlassian Rovo Dev (2025-09-02)76.8%
6EPAM AI/Run Developer Agent v20250719 + Claude 4 Sonnet76.8%
7mini-SWE-agent + Claude 4.5 Opus (high reasoning)76.8%
8ACoder76.4%
9mini-SWE-agent + Gemini 3 Flash (high reasoning)75.8%
10mini-SWE-agent + MiniMax M2.5 (high reasoning)75.8%

复杂推理 · Humanity's Last Exam — HLE 官方(lastexam.ai),CAIS + Scale AI,PhD 级难题 · 数据更新 官方持续更新 · 指标:准确率 %

#模型机构分数
1Gemini 3 Pro38.3%
2GPT-525.3%
3Grok 424.5%
4Gemini 2.5 Pro21.6%
5GPT-5-mini19.4%
6Claude 4.5 Sonnet13.7%
7Gemini 2.5 Flash12.1%
8DeepSeek-R1*8.5%
9o18.0%
10GPT-4o2.7%

今日要点

全部资讯 68

var rkTabs = document.querySelectorAll('.rk-tab'); rkTabs.forEach(function (t) { t.addEventListener('click', function () { rkTabs.forEach(function (x) { x.classList.remove('active'); }); document.querySelectorAll('.rk-panel').forEach(function (p) { p.classList.remove('active'); }); t.classList.add('active'); var el = document.getElementById(t.getAttribute('data-tab')); if (el) el.classList.add('active'); }); }); // ---------- 收藏(本地兜底 + Firebase 云同步) ---------- var FAV_KEY = 'techdaily_favs'; var favs = {}; function loadFavs() { try { favs = JSON.parse(localStorage.getItem(FAV_KEY)) || {}; } catch (e) { favs = {}; } } function saveFavs() { try { localStorage.setItem(FAV_KEY, JSON.stringify(favs)); } catch (e) {} } function favOf(link) { return favs[cleanLink(link)] || null; } function renderFavList() { var list = $('fav-list'); if (!list) return; var keys = Object.keys(favs).reverse(); list.innerHTML = keys.map(function (k) { var f = favs[k] || {}; return '
  • ' + '' + (f.title || '') + '' + '
    ' + (f.source || '') + '' + '' + (f.time || '') + '' + '
  • '; }).join(''); var sync = $('fav-sync'); if (sync) sync.textContent = '收藏保存在本机浏览器,不会上传到云端'; } function updateFavUI() { var n = Object.keys(favs).length; var c = $('fav-count'); if (c) c.textContent = n; var t = $('fav-total'); if (t) t.textContent = n; document.querySelectorAll('.fav-btn').forEach(function (b) { var on = !!favOf(b.getAttribute('data-link')); b.textContent = on ? '★' : '☆'; b.classList.toggle('active', on); }); var sec = $('favorites'); if (sec) sec.hidden = n === 0; renderFavList(); } function toggleFav(btn) { var link = cleanLink(btn.getAttribute('data-link')); if (!link) return; var li = btn.closest('.news-item'); var title = '', source = ''; if (li) { var tt = li.querySelector('.news-title'); if (tt) title = tt.textContent; var ss = li.querySelector('.src'); if (ss) source = ss.textContent; } if (favs[link]) { delete favs[link]; } else { favs[link] = { title: title, source: source, time: new Date().toLocaleString() }; } saveFavs(); updateFavUI(); } function initFavorites() { loadFavs(); updateFavUI(); } document.addEventListener('click', function (e) { var btn = e.target.closest('.fav-btn'); if (btn) { e.preventDefault(); e.stopPropagation(); toggleFav(btn); } }); var favNav = $('fav-nav-btn'); if (favNav) favNav.addEventListener('click', function () { var sec = $('favorites'); if (sec) { sec.hidden = !sec.hidden; if (!sec.hidden) sec.scrollIntoView({ behavior: 'smooth' }); } }); initFavorites(); // ---------- 回到顶部 + 全屏详情返回 ---------- var backTop = $('back-top'); if (backTop) { window.addEventListener('scroll', function () { backTop.classList.toggle('show', window.scrollY > 300); }, { passive: true }); backTop.addEventListener('click', function () { window.scrollTo({ top: 0, behavior: 'smooth' }); }); } var mBack = $('m-back'); if (mBack) mBack.addEventListener('click', closeModal); })();