Gemini 3.8 Flash Benchmark Details
Gemini 3.8 Flash currently shows benchmark results led by Terminal-Bench 2.1 (1 / 48, score 89.40), DeepSWE (1 / 33, score 73.70), LVBench (1 / 4, score 87.80). 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
AI Agent - Tool Usage
6 evaluationsProductivity Knowledge
2 evaluationsMultimodal Understanding
4 evaluationsCompetitor Comparison
Benchmark scores for Gemini 3.8 Flash compared against top models in its class
5 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Gemini 3.8 FlashCurrent | Claude Sonnet 5 | GPT-5.6 Terra | GLM-5.3-Flash |
|---|---|---|---|---|
Terminal-Bench 2.1 AI Agent - 工具使用 | 89.40Thinking Enabled ｜ Tools | 80.40Thinking Level · Extra High ｜ Tools | 87.40Thinking Level · High | 84.30Thinking Level · High ｜ Tools |
Terminal-Bench 4.0 AI Agent - 工具使用 | 19.10Thinking Enabled ｜ Tools | 12.42Thinking Level · High ｜ Tools | 21.52Thinking Level · High ｜ Tools | -- |
DeepSWE 编程与软件工程 | 73.70Thinking Enabled ｜ Tools | 54.00Deep Thinking Mode ｜ Tools | 69.60Thinking Level · Extra High ｜ Tools | 63.40Thinking Level · High ｜ Tools |
GDPval-AA v2 生产力知识 | 1545.00Thinking Enabled | -- | 1565.62Thinking Level · High ｜ Tools | 1773.00Thinking Level · High ｜ Tools |
CharXiv RQ 多模态理解 | 86.20Thinking Level · Medium | -- | -- | 89.40Thinking Level · High ｜ Tools |
Standard API Pricing: Gemini 3.8 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 3.8 Flash | DeepMind | $0.75 / 1M tokens | $3.75 / 1M tokens | — |
Claude Sonnet 5 | Anthropic | $2 / 1M tokens | $10 / 1M tokens | — |
GPT-5.6 Terra | OpenAI | $2 / 1M tokens | $12 / 1M tokens | — |
GLM-5.3-Flash | 智谱AI | $0.075 / 1M tokens | $0.25 / 1M tokens | — |
Version History
How each version of the Gemini 3.8 Flash series stacks up on benchmark tests
11 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 3.8 FlashCurrent | Gemini 3.7 Flash | Gemini 3.6 Flash | Gemini 3.5 Flash |
|---|---|---|---|---|
BioMysteryBench (Human-difficult) AI Agent - 工具使用 | 56.50Thinking Level · Medium ｜ Tools | 43.50Thinking Level · Medium ｜ Tools | -- | -- |
BioMysteryBench (Human-solvable) AI Agent - 工具使用 | 88.80Thinking Level · Medium ｜ Tools | 87.10Thinking Level · Medium ｜ Tools | -- | -- |
LABBench2 AI Agent - 工具使用 | 86.20Thinking Level · Medium ｜ Tools | 82.10Thinking Level · Medium ｜ Tools | -- | -- |
OSWorld 2.0 AI Agent - 工具使用 | 59.00Thinking Enabled ｜ Tools | 47.90Thinking Level · Medium ｜ Tools | -- | -- |
Terminal-Bench 2.1 AI Agent - 工具使用 | 89.40Thinking Enabled ｜ Tools | 85.80Thinking Enabled ｜ Tools | 78.00Thinking Enabled ｜ Tools | 76.20Thinking Level · High ｜ Tools |
DeepSWE 编程与软件工程 | 73.70Thinking Enabled ｜ Tools | 65.30Thinking Level · High ｜ Tools | 49.00Thinking Enabled ｜ Tools | 37.00Thinking Level · Medium ｜ Tools |
GDPval-AA v2 生产力知识 | 1545.00Thinking Enabled | 1525.00Thinking Enabled | 1421.00Thinking Enabled | 1349.00Thinking Enabled |
CharXiv RQ 多模态理解 | 86.20Thinking Level · Medium | 88.70Thinking Level · Medium ｜ Tools | 89.40Thinking Enabled ｜ Tools | 84.90Thinking Enabled ｜ Tools |
GDP.pdf 多模态理解 | 35.00Thinking Level · Medium | 34.00Thinking Level · Medium | -- | -- |
LVBench 多模态理解 | 87.80Thinking Level · Medium ｜ Tools | 85.40Thinking Level · Medium | -- | -- |
HLE-Verified 综合评估 | 54.90Thinking Level · Medium | 53.60Thinking Level · Medium | -- | -- |
Single-Benchmark Version Trend
Viewing: BioMysteryBench (Human-difficult) · AI Agent - 工具使用
Standard API Pricing Across the Gemini 3.8 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 3.8 Flash | DeepMind | $0.75 / 1M tokens | $3.75 / 1M tokens | — |
Gemini 3.7 Flash | DeepMind | $0.75 / 1M tokens | $3.75 / 1M tokens | — |
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 | — |