Kad model DeepMind Gemini 3.5 Flash. · sumber
Kad model DeepMind Gemini 3.5 Flash. · sumber
Kad model DeepMind Gemini 3.5 Flash. · sumber
Kad model DeepMind Gemini 3.5 Flash. · sumber
Estimate from the version's published specs, benchmarks and reviews, 0-5; scores are only comparable within one criteria year. Scored as launched (19 May 2026). Reasoning: Artificial Analysis Intelligence Index 55 at launch (AA launch article; ahead of Grok 4.3 53). Coding null: no Terminal-Bench 4.0; Google published Terminal-bench 2.1 76.2% (Terminus-2) and SWE-Bench Pro 55.1%; AA's own Coding Index was 45, not an anchor figure. Context 1M tokens. Price $1.50 in / $9 out per 1M = $3.375 blended (AA; 3x Gemini 3 Flash). Speed over 280 output tokens/s measured by Artificial Analysis at launch. Input text, image, video, speech (AA). Pin sourceUrl is TechCrunch; the model card is used here as maker page and was opened this run.[3]
Gemini 3.5 Flash scores 55 on the Artificial Analysis Intelligence Index, up 9 points from Gemini 3 Flash, driven primarily by agentic performance gains and hallucination reduction.
Gemini 3.5 Flash burns through so many more tokens on agent-based tasks that total costs end up 75 percent higher than Gemini 3.1 Pro, according to Artificial Analysis.
Gemini tracked each stream independently while periodically merging findings into an evolving assessment summary.
That speed is central to Flash's design for agentic work, where multiple AI agents run at the same time on long-running tasks, according to Kavukcuoglu.
| Gemini 3.5 Flash: The new leader in intelligence versus speed · 19 Mei 2026 | 0.80 |
|---|---|
| With Gemini 3.5 Flash, Google bets its next AI wave on agents, not chatbots · 19 Mei 2026 | 0.40 |
| Google's Gemini 3.5 Flash follows Anthropic and OpenAI in making newer AI models significantly pricier · 20 Mei 2026 | -0.30 |
| 5 prompts that show how the new Gemini 3.5 Flash is its best AI model yet · 21 Mei 2026 | 0.40 |
Foto daripada pembaca, berasingan daripada media bersumber pin. Nilaikan apa yang anda makan atau lihat, dan pada pin restoran, tag hidangan terus pada foto anda.
Entri pertama sentiasa sumber pin. Keyakinan keseluruhan ialah purata berpemberat bagi sejauh mana setiap rujukan menyokong masa mula dan tamat yang digunakan di atas; sesebuah rujukan diambil kira separuh kurang bagi setiap 180 hari lebih lama daripada yang terbaharu.
TechCrunch melaporkan Google melancarkan Gemini 3.5 Flash pada Selasa 19 Mei 2026 di persidangan pembangun tahunan I/O-nya; kad model Google DeepMind[3] untuk 3.5 Flash diterbitkan pada hari yang sama.
The Wikipedia article lists Gemini 3.5 Flash as released on 19 May 2026, based on Gemini 3 Flash.
DeepMind's model card, published 19 May 2026, gives the benchmark results against Gemini 3 Flash, 3.1 Pro, Claude Sonnet 4.6, Claude Opus 4.7 and GPT-5.5.
Ada yang tertinggal atau salah? Nyatakan dengan kata-kata anda sendiri: pautan yang menyokong pin ini, tarikh mula atau tamat yang berbeza beserta sebabnya, atau fakta yang tiada atau tersilap. AI menyemaknya berbanding sumber pin ini, mencari yang lebih baik, dan menambah mana-mana halaman yang menyokong anda. Sumber pin itu sendiri tetap paling diambil kira. Gambar yang menunjukkan sesuatu yang lain, atau menunjukkannya dengan buruk, turut dilihat, dan dialihkan ke bawah atau diganti.
Tajuk asal: Gemini 3.5 Flash Released
| Penanda aras | Gemini 3.5 Flash | Gemini 3 Flash | Gemini 3.1 Pro | Claude Sonnet 4.6 | Claude Opus 4.7 | GPT-5.5 |
|---|---|---|---|---|---|---|
| Terminal-bench 2.1 (Pengekodan terminal agentik, harness Terminus-2) | 76.2% | 58.0% | 70.3% | — | 66.1% | 78.2% |
| SWE-Bench Pro (Public) (Pelbagai tugas pengekodan agentik, percubaan tunggal) | 55.1% | 49.6% | 54.2% | — | 64.3% | 58.6% |
| MCP Atlas (Aliran kerja berbilang langkah menggunakan MCP) | 83.6% | 62.0% | 78.2% | 69.5% | 79.1% | 75.3% |
| Toolathlon (Penggunaan alat umum dunia sebenar) | 56.5% | 49.4% | — | — | — | 55.6% |
| OSWorld-Verified (Penggunaan komputer agentik) | 78.4% | 65.1% | 76.2% | 72.5% | 78.0% | 78.7% |
| Finance Agent v2 (Analisis kewangan dan pembuatan keputusan) | 57.9% | 42.6% | 43.0% | 51.0% | 51.5% | 51.8% |
| GDPval-AA (Kerja pengetahuan bernilai ekonomi, Elo) | 1656 | 1204 | 1314 | 1676 | 1753 | 1769 |
| CharXiv Reasoning (Sintesis maklumat daripada carta kompleks, tanpa alat) | 84.2% | 80.3% | 83.3% | 72.4% | 82.1% | 84.1% |
| MMMU-Pro (Pemahaman dan penaakulan multimodal, tanpa alat) | 83.6% | 81.2% | 80.5% | 74.5% | 75.2% | 81.2% |
| Blueprint-Bench 2 (Penaakulan ruang agentik, skor ternormal) | 33.6% | 0.0% | 26.5% | 6.7% | 24.5% | 36.2% |
| MRCR v2 (8-needle) (Prestasi konteks panjang, 128k (purata)) | 77.3% | 67.2% | 84.9% | 84.9% | 59.3% | 94.8% |
| MRCR v2 (8-needle) (Prestasi konteks panjang, 1M (titik demi titik)) | 26.6% | 22.1% | 26.3% | — | — | — |
| Humanity’s Last Exam (Penaakulan akademik (set penuh, teks + MM)) | 40.2% | 33.7% | 44.4% | 33.2% | 46.9% | 41.4% |
| ARC-AGI-2 (Teka-teki penaakulan abstrak) | 72.1% | 33.6% | 77.1% | 58.3% | 75.8% | 84.6% |