Gemini 3.6 Flash Benchmark Details
Gemini 3.6 Flash currently shows benchmark results led by GPQA Diamond (8 / 271, score 94.13), Context Arena (17 / 126, score 88.78), OSWorld-Verified (5 / 26, score 83). This page also compares it with 3 competitor models and 3 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
Writing and Creative Capabilities
1 evaluationsCoding and Software Engineer
3 evaluationsText Embedding
3 evaluationsAI Agent - Tool Usage
3 evaluationsMultimodal Understanding
2 evaluationsOther
2 evaluationsMath and Reasoning
2 evaluationsCompetitor Comparison
Benchmark scores for Gemini 3.6 Flash compared against top models in its class
11 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Gemini 3.6 FlashCurrent | GPT-5.6 Terra | Claude Sonnet 5 | Grok 4.5 |
|---|---|---|---|---|
GPQA Diamond 科学与综合推理 | 94.13Thinking Level · High | 93.31Thinking Level · High | 90.53Thinking Level · Extra High | 93.43Thinking Level · High |
Creative Writing 写作和创作 | 1599.70Standard Mode | 1850.00Standard Mode | 1787.60Standard Mode | 1576.00Standard Mode |
DeepSWE 编程与软件工程 | 49.00Thinking Enabled ｜ Tools | 69.60Thinking Level · Extra High ｜ Tools | 54.00Deep Thinking Mode ｜ Tools | 53.00Thinking Level · High ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 58.70Thinking Enabled ｜ Tools | -- | -- | 64.70Thinking Level · High ｜ Tools |
WeirdML v2 编程与软件工程 | 56.10Thinking Level · High ｜ Tools | 78.27Thinking Level · High ｜ Tools | 68.78Thinking Level · High ｜ Tools | -- |
Context Arena 文本向量检索 | 88.78Thinking Level · High | 92.17Thinking Level · High | 79.53Thinking Level · High | -- |
OSWorld-Verified AI Agent - 工具使用 | 83.00Thinking Enabled ｜ Tools | -- | 81.20Thinking Level · Extra High ｜ Tools | -- |
Terminal-Bench 2.1 AI Agent - 工具使用 | 78.00Thinking Enabled ｜ Tools | 87.40Thinking Level · High | 80.40Thinking Level · Extra High ｜ Tools | 83.30Thinking Level · High ｜ Tools |
GDPval-AA v2 生产力知识 | 1421.00Thinking Enabled | 1565.62Thinking Level · High ｜ Tools | -- | 1526.00Thinking Level · High ｜ Tools |
21.95Thinking Level · High | 70.73Thinking Level · High | 29.27Thinking Level · High | 24.39Thinking Level · High | |
FrontierMath v2 数学推理 | 58.95Thinking Level · High | 85.96Thinking Level · High | 65.61Thinking Level · High | 57.19Thinking Level · High |
Standard API Pricing: Gemini 3.6 Flash vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Gemini 3.6 Flash | DeepMind | $1.5 / 1M tokens | $7.5 / 1M tokens | — |
GPT-5.6 Terra | OpenAI | $2 / 1M tokens | $12 / 1M tokens | — |
Claude Sonnet 5 | Anthropic | $2 / 1M tokens | $10 / 1M tokens | — |
Grok 4.5 | xAI | $2 / 1M tokens | $6 / 1M tokens | — |
Version History
How each version of the Gemini 3.6 Flash series stacks up on benchmark tests
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | Gemini 3.6 FlashCurrent | Gemini 3.5 Flash | Gemini 3.0 Flash |
|---|---|---|---|
GPQA Diamond 科学与综合推理 | 94.13Thinking Level · High | 92.80Thinking Level · High | 90.40Thinking Enabled |
DeepSWE 编程与软件工程 | 49.00Thinking Enabled ｜ Tools | 37.00Thinking Level · Medium ｜ Tools | -- |
SWE-Bench Pro - Public 编程与软件工程 | 58.70Thinking Enabled ｜ Tools | 55.10Thinking Level · High ｜ Tools | 49.60Thinking Level · High ｜ Tools |
WeirdML v2 编程与软件工程 | 56.10Thinking Level · High ｜ Tools | -- | 61.60Standard Mode ｜ Tools |
Context Arena 文本向量检索 | 88.78Thinking Level · High | 77.19Thinking Level · High | -- |
MLE-Bench AI Agent - 工具使用 | 63.90Thinking Enabled ｜ Tools | 49.70Thinking Enabled ｜ Tools | -- |
OSWorld-Verified AI Agent - 工具使用 | 83.00Thinking Enabled ｜ Tools | 78.40Thinking Level · High ｜ Tools | -- |
Terminal-Bench 2.1 AI Agent - 工具使用 | 78.00Thinking Enabled ｜ Tools | 76.20Thinking Level · High ｜ Tools | 58.00Thinking Level · High ｜ Tools |
GDPval-AA v2 生产力知识 | 1421.00Thinking Enabled | 1349.00Thinking Enabled | -- |
CharXiv RQ 多模态理解 | 89.40Thinking Enabled ｜ Tools | 84.90Thinking Enabled ｜ Tools | -- |
91.80Thinking Enabled | 77.30Thinking Enabled | -- | |
54.00Thinking Enabled | 26.60Thinking Enabled | -- |
Single-Benchmark Version Trend
Viewing: GPQA Diamond · 科学与综合推理
Standard API Pricing Across the Gemini 3.6 Flash Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Gemini 3.6 Flash | DeepMind | $1.5 / 1M tokens | $7.5 / 1M tokens | — |
Gemini 3.5 Flash | DeepMind | $1.5 / 1M tokens | $9 / 1M tokens | — |
Gemini 3.0 Flash | Google Deep Mind | $0.5 / 1M tokens | $3 / 1M tokens | — |