DeepSeek-V4-Pro Benchmark Details
DeepSeek-V4-Pro currently shows benchmark results led by LiveCodeBench (1 / 123, score 93.50), MMLU Pro (11 / 132, score 87.50), SWE-bench Verified (11 / 112, score 80.60). This page also compares it with 2 competitor models and 3 predecessor or same-series models, including performance and pricing views when available. 1 source link is attached for reference.
Benchmark Results
Benchmark Results
General Knowledge
12 evaluationsCoding and Software Engineer
14 evaluationsAI Agent - Information Search
2 evaluationsAI Agent - Tool Usage
3 evaluationsMath and Reasoning
3 evaluationsCompetitor Comparison
Benchmark scores for DeepSeek-V4-Pro compared against top models in its class
10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | DeepSeek-V4-ProCurrent | GLM 5.1 | Kimi K2.6 |
|---|---|---|---|
GPQA Diamond 综合评估 | 90.10Thinking Level · High | 86.20Thinking Enabled | 90.50Thinking Enabled |
HLE 综合评估 | 48.20Thinking Level · Extra High ｜ Tools | 52.30Thinking Enabled ｜ Tools | 54.00Thinking Enabled ｜ Tools |
LiveBench 综合评估 | 73.58Standard Mode | 70.18Standard Mode | 72.17Thinking Enabled |
LiveCodeBench 编程与软件工程 | 93.50Thinking Level · High | -- | 89.60Thinking Enabled |
SWE-bench Multilingual 编程与软件工程 | 76.20Thinking Level · Extra High ｜ Tools | -- | 76.70Thinking Enabled ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 55.40Thinking Level · Extra High ｜ Tools | 58.40Thinking Enabled ｜ Tools | 58.60Thinking Enabled ｜ Tools |
SWE-bench Verified 编程与软件工程 | 80.60Thinking Level · Extra High ｜ Tools | -- | 80.20Thinking Enabled ｜ Tools |
BrowseComp AI Agent - 信息收集 | 83.40Thinking Level · Extra High ｜ Tools | 79.30Thinking Enabled ｜ Tools | 83.20Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 67.90Thinking Level · Extra High ｜ Tools | 63.50Thinking Enabled ｜ Tools | 66.70Thinking Enabled ｜ Tools |
IMO-AnswerBench 数学推理 | 89.80Thinking Level · High | 83.80Thinking Enabled | 86.00Thinking Enabled |
Standard API Pricing: DeepSeek-V4-Pro 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 |
|---|---|---|---|---|
DeepSeek-V4-Pro | DeepSeek-AI | $0.435 / 1M tokens | $0.87 / 1M tokens | — |
GLM 5.1 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
Kimi K2.6 | Facebook AI研究实验室 | $0.95 / 1M tokens | $4 / 1M tokens | — |
Version History
How each version of the DeepSeek-V4-Pro 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 | DeepSeek-V4-ProCurrent | DeepSeek V3.2 | DeepSeek-V3.1 | DeepSeek-R1-0528 |
|---|---|---|---|---|
GPQA Diamond 综合评估 | 90.10Thinking Level · High | 82.40Thinking Enabled | 80.10Thinking Enabled | 81.00Thinking Enabled |
HLE 综合评估 | 48.20Thinking Level · Extra High ｜ Tools | 25.10Thinking Enabled | 15.90Thinking Enabled | 17.70Thinking Enabled |
LiveBench 综合评估 | 73.58Standard Mode | 62.20Thinking Enabled | -- | -- |
MMLU Pro 综合评估 | 87.50Thinking Level · High | -- | 85.00Thinking Enabled | 85.00Thinking Enabled |
CodeForces 编程与软件工程 | 3206.00Thinking Level · High | 2386.00Thinking Enabled | -- | -- |
LiveCodeBench 编程与软件工程 | 93.50Thinking Level · High | 83.30Thinking Enabled | 74.80Thinking Enabled | 73.30Thinking Enabled |
SWE-Bench Pro - Public 编程与软件工程 | 55.40Thinking Level · Extra High ｜ Tools | 40.90Thinking Enabled | -- | -- |
SWE-bench Verified 编程与软件工程 | 80.60Thinking Level · Extra High ｜ Tools | 73.10Thinking Enabled ｜ Tools | 66.00Standard Mode | 57.60Thinking Enabled |
Simple Bench 常识推理 | 50.90Standard Mode | -- | 40.00Standard Mode | 40.80Thinking Enabled |
BrowseComp AI Agent - 信息收集 | 83.40Thinking Level · Extra High ｜ Tools | 51.40Thinking Enabled | -- | -- |
Terminal Bench 2.0 AI Agent - 工具使用 | 67.90Thinking Level · Extra High ｜ Tools | 46.40Thinking Enabled ｜ Tools | -- | -- |
Single-Benchmark Version Trend
Viewing: GPQA Diamond · 综合评估
Standard API Pricing Across the DeepSeek-V4-Pro 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 |
|---|---|---|---|---|
DeepSeek-V4-Pro | DeepSeek-AI | $0.435 / 1M tokens | $0.87 / 1M tokens | — |
DeepSeek V3.2 | DeepSeek-AI | $0.28 / 1M tokens | $0.42 / 1M tokens | — |
DeepSeek-V3.1 | Fireworks AI | $0.56 / 1M tokens | $1.68 / 1M tokens | — |
DeepSeek-R1-0528 | Fireworks AI | $1.35 / 1M tokens | $5.4 / 1M tokens | — |