Ruka hadi maudhui makuu
BTC $82,480.01 -0.39% ETH $2,495.58 -2.82% BNB $741.72 -3.61% XRP $1.40 -1.40% SOL $110.55 -4.45% TRX $0.3322 -1.07% HYPE $85.45 -2.67% ZEC $1,220.80 -5.91% DOGE $0.0850 -4.18% XMR $539.74 -3.60% WBTC $82,376.55 -0.44% LINK $12.85 -2.45% ADA $0.2357 -7.46% LEO $8.90 -0.20% WBT $85,387.00 +8.60% XLM $0.1946 -2.31% NEAR $4.77 -10.99% BCH $278.90 -6.60% LTC $63.87 -2.37% CC $0.1192 +1.76%
iCute FinanceMALI ZA KIDIJITALI · UCHUNGUZI WA SOKO
Kiswahili
中文繁體中文English日本語한국어EspañolPortuguês (Brasil)РусскийTürkçeFrançaisDeutschहिन्दीالعربيةবাংলাBahasa IndonesiaBahasa MelayuاردوTiếng ViệtไทยItalianoفارسیதமிழ்తెలుగుमराठीਪੰਜਾਬੀKiswahiliHausaYorùbáአማርኛ
Saraka ya utafiti
iCute Finance

Urambazaji mkuu

Urambazaji mkuu
Nyumbani Saraka ya utafiti
MALI ZA KIDIJITALI · UCHUNGUZI WA SOKO

DeepSeek V4.1 Flash, the new version, tops the Agent Arena open-source model leaderboard and ranks 11th overall.

PANewsdakika 2 kusoma

PANews October 20 news: The AI model evaluation platform Arena announced that DeepSeek-V4.1-Flash-20261017 (Max) has ranked first among open-source models on Agent Arena and 11th on the overall leaderboard. Based on approximately 7,500 real usage sessions, the model's comprehensive net improvement relative to the average model is about 5.1%, and the median cost per task is about $0.20. This version ranks first among open-source models in all four metrics: task success confirmation, positive and negative user feedback, Bash command execution reliability, and steerability, with the task success confirmation metric ranking 8th on the overall leaderboard.

PANews October 20 news: The AI model evaluation platform Arena announced that DeepSeek-V4.1-Flash-20261017 (Max) has ranked first among open-source models on Agent Arena and 11th on the overall leaderboard. Based on approximately 7,500 real usage sessions, the model's comprehensive net improvement relative to the average model is about 5.1%, and the median cost per task is about $0.20. This version ranks first among open-source models in all four metrics: task success confirmation, positive and negative user feedback, Bash command execution reliability, and steerability, with the task success confirmation metric ranking 8th on the overall leaderboard.

Habari zinazohusiana

  1. Ukandamizaji wa Kifedha katika Enzi ya AI

    📺 Tazama Video Bitcoin Magazine Ukandamizaji wa Kifedha katika Enzi ya AI Uhamishaji wa kazi nje uliifanya Marekani kutegemea wapinzani kwa teknolojia muhimu, asema Craig Tindale....

    Bitcoin Magazine

  2. Uuzaji wa Hati za Hazina za Marekani za Septemba: Sio Matarajio ya Mfumuko wa Bei, Bali Kuongezeka kwa Mavuno Halisi

    Soko linaweza kuwa linatathmini upya ukuaji wa uchumi na mahitaji ya mtaji, lakini malipo ya ziada ya muda yanasalia kuwa wasiwasi.

    BLOCKBEATS

  3. Wanyang'anyi watatu wenye silaha huko Pattaya, Thailand, walimlazimisha raia wa China kuhamisha dola 820,000 katika sarafu ya kidijitali.

    ODAILY

  4. TRAE ya ByteDance inaunganisha zana mbili za AI, TraeWork itafungwa tarehe 23 Oktoba.

    BLOCKBEATS

  5. Bernstein: Mapato ya TSMC kwa robo ya tatu yanatarajiwa kufikia NT$1.49 trilioni, 3% juu ya makubaliano ya soko.

    BLOCKBEATS