Kartu model Flash DeepMind Gemini 3.5. · sumber
Kartu model Flash DeepMind Gemini 3.5. · sumber
Kartu model Flash DeepMind Gemini 3.5. · sumber
Kartu model Flash DeepMind Gemini 3.5. · 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 dari pembaca, terpisah dari media bersumber milik pin. Nilai apa yang Anda makan atau lihat, dan di pin restoran, tandai hidangan langsung pada foto Anda.
Entri pertama selalu merupakan sumber pin. Keyakinan keseluruhan adalah rata-rata tertimbang dari seberapa kuat setiap referensi mendukung waktu mulai dan berakhir yang digunakan di atas; bobot sebuah referensi berkurang setengahnya untuk setiap 180 hari lebih lama dari yang terbaru.
TechCrunch melaporkan Google meluncurkan Gemini 3.5 Flash pada Selasa 19 Mei 2026 di konferensi pengembang tahunan I/O; model card 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 kurang atau salah? Sampaikan dengan kata-kata Anda sendiri: tautan yang mendukung pin ini, tanggal mulai atau berakhir yang berbeda beserta alasannya, atau fakta yang kurang atau keliru. AI memeriksanya terhadap sumber pin ini, mencari sumber yang lebih baik, dan menambahkan halaman mana pun yang mendukung Anda. Sumber pin itu sendiri tetap paling diperhitungkan. Gambar yang menampilkan hal lain, atau menampilkannya dengan buruk, juga diperiksa, lalu diturunkan atau diganti.
Judul asli: Gemini 3.5 Flash Released
| Tolok ukur | 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 (Pengodean terminal agentik, harness Terminus-2) | 76.2% | 58.0% | 70.3% | — | 66.1% | 78.2% |
| SWE-Bench Pro (Public) (Beragam tugas pengodean agentik, satu percobaan) | 55.1% | 49.6% | 54.2% | — | 64.3% | 58.6% |
| MCP Atlas (Alur kerja multilangkah memakai MCP) | 83.6% | 62.0% | 78.2% | 69.5% | 79.1% | 75.3% |
| Toolathlon (Penggunaan alat umum di dunia nyata) | 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 keuangan dan pengambilan keputusan) | 57.9% | 42.6% | 43.0% | 51.0% | 51.5% | 51.8% |
| GDPval-AA (Pekerjaan pengetahuan bernilai ekonomi, Elo) | 1656 | 1204 | 1314 | 1676 | 1753 | 1769 |
| CharXiv Reasoning (Sintesis informasi dari grafik kompleks, tanpa alat) | 84.2% | 80.3% | 83.3% | 72.4% | 82.1% | 84.1% |
| MMMU-Pro (Pemahaman dan penalaran multimodal, tanpa alat) | 83.6% | 81.2% | 80.5% | 74.5% | 75.2% | 81.2% |
| Blueprint-Bench 2 (Penalaran spasial agentik, skor ternormalisasi) | 33.6% | 0.0% | 26.5% | 6.7% | 24.5% | 36.2% |
| MRCR v2 (8-needle) (Kinerja konteks panjang, 128k (rata-rata)) | 77.3% | 67.2% | 84.9% | 84.9% | 59.3% | 94.8% |
| MRCR v2 (8-needle) (Kinerja konteks panjang, 1M (pointwise)) | 26.6% | 22.1% | 26.3% | — | — | — |
| Humanity’s Last Exam (Penalaran akademik (set penuh, teks + MM)) | 40.2% | 33.7% | 44.4% | 33.2% | 46.9% | 41.4% |
| ARC-AGI-2 (Teka-teki penalaran abstrak) | 72.1% | 33.6% | 77.1% | 58.3% | 75.8% | 84.6% |