Nilai daripada jadual kad model Gemini 3.7 Flash DeepMind. · sumber
Nilai daripada jadual kad model Gemini 3.7 Flash DeepMind. · sumber
Nilai daripada jadual kad model Gemini 3.7 Flash DeepMind. · sumber
| Model | Input $/1J | Output $/1J | Indeks Kecerdasan Analisis Buatan |
|---|---|---|---|
| Gemini 3.7 Flash | $0.75 (pengenalan) | $3.75 (pengenalan) | 56 |
| Gemini 3.6 Flash | $0.75 (pengenalan) | $3.75 (pengenalan) | 52 |
| Claude Sonnet 5 | $2.00 | $10.00 | 55 |
| GPT-5.6 Terra | $2.00 | $12.00 | 57 |
| Muse Spark 1.2 | $1.25 | $4.25 | 57 |
Seperti yang disenaraikan dalam kad model DeepMind; Harga Google ialah harga pengenalan sehingga akhir tahun 2026. · sumber
Estimate from the version's published specs, benchmarks and reviews, 0-5; scores are only comparable within one criteria year. Scored as launched (Gemini 3.7 Flash, 13 Aug 2026): Artificial Analysis Intelligence Index 56 at high reasoning (AA article of 13 Aug; its model page now shows 39 on v4.3.2, not used); 1M-token context; launch list price was the introductory $0.75 in / $3.75 out per 1M through end of 2026 = $1.50 blended at 3:1 (scored 4.5); the standard $1.50/$7.50 = $3.00 blended would score 4; about 340 output tokens/s per AA; text, image, video, speech input. Coding null: no Terminal-Bench 4.0 at launch (Google 85.8% on Terminal-bench 2.1; 14.9% on 3.0). Reviews: AA's note, a Bijan Bowen hands-on video (summary page), buildfastwithai; one hands-on source only.[1]
Gemini 3.7 Flash (high) scores 56 on the Artificial Analysis Intelligence Index, just behind GPT-5.6 Terra (max, 57) and Muse Spark 1.2 (xhigh, 57)
Gemini 3.7 Flash is fast and comparatively inexpensive, but its hands-on coding results improve on its predecessor without reaching uniformly reliable frontier performance.
Gemini 3.7 Flash is a genuine upgrade over 3.6 Flash, with large gains on coding and agent benchmarks like DeepSWE
| Gemini 3.7 Flash: On the Intelligence vs. Time per Task Pareto frontier · 13 Ogo 2026 | 0.40 |
|---|---|
| Gemini 3.7 Flash Review: Benchmarks, Price & the Catch (2026) · 13 Ogo 2026 | 0.70 |
| Gemini 3.7 Flash Is Here: Testing Google's Best Model Yet (Bijan Bowen, video summary page) · 17 Ogo 2026 | 0.20 |
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.
Laporan pelancaran 9to5Google bertarikh 13 Ogos 2026 dan menyatakan Google "hari ini mengumumkan Gemini 3.7 Flash"; kad model DeepMind[2] diterbitkan pada 13 Ogos 2026.
DeepMind's model card, published 13 August 2026, lists the introductory prices and a benchmark table against 3.6 Flash, Claude Sonnet 5, GPT-5.6 Terra and Muse Spark 1.2.
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 3.7 Flash Released
| Penanda aras | Gemini 3.7 Flash | Gemini 3.6 Flash | Claude Sonnet 5 | GPT-5.6 Terra | Muse Spark 1.2 |
|---|---|---|---|---|---|
| Harga input ($/1M token) | $0.75* | $0.75* | $2.00 | $2.00 | $1.25 |
| Harga output ($/1M token) | $3.75* | $3.75* | $10.00 | $12.00 | $4.25 |
| Artificial Analysis Intelligence Index (Kecerdasan model komposit) | 56 | 52 | 55 | 57 | 57 |
| FrontierCode 1.1 Main (Kualiti kod pengeluaran, Skor) | 43.6% | 34.4% | 42.7% | 41.3% | — |
| DeepSWE v1.1 (Kejuruteraan perisian jangka panjang) | 65.3% | 48.6% | 53.8% | 69.6% | 54.9% |
| Code Arena (Pembangunan web, Elo) | 1588 | 1538 | 1541 | 1523 | 1535 |
| Terminal-bench 2.1 (Pengekodan terminal agentik) | 85.8% | 78.0% | 80.4% | 87.4% | 82.9% |
| Terminal-bench 3.0 (Keupayaan agen umum) | 14.9% | 5.4% | 14.6% | 20.8% | — |
| AutomationBench (Automasi aliran kerja perusahaan, set persendirian) | 30.4% | 17.0% | 10.7% | 23.6% | — |
| GDPVal-AA v2 (Kerja pengetahuan, Elo) | 1525 | 1422 | 1598 | 1578 | 1628 |
| Harvey LAB-AA (Aliran kerja undang-undang kompleks) | 90.7% | 85.1% | 90.1% | 85.2% | — |
| GDP.pdf (Kefahaman dokumen PDF pakar) | 34.0% | 22.0% | 28.0% | 24.7% | 16.0% |
| CharXiv Reasoning (Sintesis maklumat daripada carta kompleks, tanpa alat) | 84.5% | 85.2% | 77.0% | 85.9% | — |
| CharXiv Reasoning (Sintesis maklumat daripada carta kompleks, dengan alat) | 88.7% | 89.4% | 88.3% | — | — |
| LVBench (Kefahaman video panjang) | 85.4% | 84.2% | 68.5% | 78.9% | — |
| GDM-MRCR v2 (8-needle) (Prestasi konteks panjang, 128k (purata)) | 97.0% | 91.8% | 81.5% | 93.5% | — |
| OSWorld-2.0 (Penggunaan komputer agentik) | 47.9% | 33.8% | — | 50.2% | — |
| Agent's Last Exam (Tugas agen desktop dan OS multimodal, kadar lulus) | 26.3% | 24.2% | 33.3% | 28.0% | — |
| HLE-Verified (Penaakulan pakar pelbagai disiplin) | 53.6% | 51.2% | 31.0% | 51.1% | — |
| BioMysteryBench (Penaakulan penyelidikan bioinformatik, boleh diselesaikan manusia) | 87.1% | 80.6% | 87.5% | 83.8% | — |
| BioMysteryBench (Penaakulan penyelidikan bioinformatik, sukar bagi manusia) | 43.5% | 41.2% | 34.1% | 49.4% | — |
| LABBench2 (Tugas penyelidikan biologi dunia sebenar) | 82.1% | 76.1% | 80.1% | 81.2% | — |