Model dossier模型档案
Gemini 3.5 Flash
Gemini 3.5 Flash is a high-tier model from Google (Intelligence Score 83.6/100). Strongest in agent (96.8) and knowledge (96.7); best fit: tool-use and multi-step agents. Premium-priced: $1.50 in / $9.00 out per 1M tokens. Context window 1M tokens — long-document friendly.
Gemini 3.5 Flash 是 Google 的高水平梯队模型(智能评分 83.6/100)。 最强项是智能体(96.8分),其次是知识(96.7分);适合工具调用与多步 Agent。 定价属高端定价:每百万 token 输入 $1.50 / 输出 $9.00。 上下文 1M token,长文档友好。
83.6
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 95%
◈
Benchmark scoresBenchmark 成绩
10 entries 条| Benchmark基准 | Score成绩 | Index指数 | Dated日期 | Measured by测评方 | |
|---|---|---|---|---|---|
| Humanity's Last ExamReasoning | 40.2 | 70 | — | 3rd-party第三方 | source ↗×4 |
| GPQA DiamondReasoning | 92.2⚡high | 97 | — | 3rd-party第三方 | source ↗×5 |
| MMLU-ProKnowledge | 89.58 | 97 | — | 3rd-party第三方 | source ↗ |
| SWE-bench VerifiedCoding | 78 | 81 | — | 3rd-party第三方 | source ↗×4⚠±10.3 |
| AIME 2025Math | 96.67 | 97 | — | 3rd-party第三方 | source ↗×3 |
| LiveCodeBenchCoding | 87.6 | 94 | — | 3rd-party第三方 | source ↗×3⚠±45.21 |
| FrontierMathMath | 38.966 | 41 | — | 3rd-party第三方 | source ↗ |
| Terminal-BenchCoding | 76.2 | 83 | 2026-07 | 3rd-party第三方 | source ↗×2 |
| τ²-benchAgent | 95.3 | 97 | — | 3rd-party第三方 | source ↗×4⚠±20.6 |
| ↳ ⚡medium | 95.6 | — | 2026-06-10 | 3rd-party第三方 | source ↗ |
| LMArena (Chatbot Arena)Preference | 1477 | 64 | 2026-08-12 | official官方榜 | source ↗×6 |
| ↳ ⚡high | 1480 | — | — | 3rd-party第三方 | source ↗ |
≡
Specs & pricing规格与价格
| Provider厂商 | |
|---|---|
| Released发布 | 2026-05-19 |
| Context window上下文 | 1M tokens |
| Max output最大输出 | 66K tokens |
| Modality模态 | text+image+file+audio+video->text |
| Reasoning tiers推理档位 | ⚡low ⚡medium ⚡high default默认 high · minimal / low / medium / high |
| API input price输入价格 | $1.50 / 1M tokens |
| API output price输出价格 | $9.00 / 1M tokens |
⛓
Tools using this model使用它的工具
How we score →评分方法 → · Catalog & pricing via the official OpenRouter API.模型目录与价格来自 OpenRouter 官方 API。