DeepSeek, open weights

# DeepSeek V4 Pro

> DeepSeek V4 Pro by DeepSeek, released April 2026. Ranked #31 of 354 with a Noometry Index of 54.3. API: $0.66 in / $1.98 out per M tokens. 1M context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/deepseek-v4-pro
- Last updated: 2026-10-10
- Title: DeepSeek V4 Pro Benchmarks, Price & Rank (October 2026)

DeepSeek V4 Pro by DeepSeek ranks 31st of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.3. Its strongest category is reasoning, where it ranks 24th. API pricing starts at $0.66 per million input tokens and $1.98 per million output tokens, with a 1M-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #31 of 354
- **Index score:** 54.3
- **Evidence:** Confirmed 48 results
- **Provider:** [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek)
- **Released:** April 24, 2026
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 1M
- **Max output:** 393K
- **Input price:** $0.66 / M
- **Output price:** $1.98 / M
- **Blended price:** $0.99 / M
- **Output speed:** 16 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #92 of 219
- **Knowledge cutoff:** May 2025
- **Input:** text
- **Hugging Face:** [deepseek-ai/DeepSeek-V4-Pro](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro)

## Category scores

Each category score combines every public result we have in that category.

DeepSeek V4 Pro category scores

1.  Coding 52.4
2.  Agentic & Tool Use 32.8
3.  Reasoning 56.5
4.  Math 64.8
5.  Knowledge 59.5
6.  Multilingual 54.4
7.  Instruction Following 76.1
8.  Long Context 45.0
9.  Writing & Preference 65.5
10.  020406080

DeepSeek V4 Pro category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 52.4 | #34 | 6 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 32.8 | #58 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 56.5 | #24 | 11 |
| [Math](https://noometry.com/best/math) | 64.8 | #30 | 6 |
| [Knowledge](https://noometry.com/best/knowledge) | 59.5 | #31 | 4 |
| [Multilingual](https://noometry.com/best/multilingual) | 54.4 | #45 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 76.1 | #47 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 45.0 | #51 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 65.5 | #46 | 5 |

## Strengths and weaknesses

Categories where DeepSeek V4 Pro places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

DeepSeek V4 Pro: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 56.5 | +32.9 | #24 of 350, top 7% |
| [Math](https://noometry.com/best/math) | 64.8 | +28.3 | #30 of 327, top 10% |
| [Knowledge](https://noometry.com/best/knowledge) | 59.5 | +22.2 | #31 of 314, top 10% |

### Weakest categories

DeepSeek V4 Pro: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 32.8 | +2.5 | #58 of 154, top 38% |
| [Long Context](https://noometry.com/best/long-context) | 45.0 | +4.0 | #51 of 296, top 18% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 76.1 | +4.9 | #47 of 305, top 16% |

## Closest competitors

The models ranked just above and below DeepSeek V4 Pro. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to DeepSeek V4 Pro
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Muse Spark 1.3](https://noometry.com/models/muse-spark-1-3) | #27 | 54.8 | $2 | — | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-muse-spark-1-3) |
| [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) | #28 | 54.8 | — | 1 | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-pro) |
| [Claude Sonnet 5](https://noometry.com/models/claude-sonnet-5) | #29 | 54.6 | $4 | — | [Compare](https://noometry.com/compare/claude-sonnet-5-vs-deepseek-v4-pro) |
| [GPT-5.6 Luna](https://noometry.com/models/gpt-5-6-luna) | #30 | 54.6 | $0.45 | 12 | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-6-luna) |
| [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash) | #32 | 54.2 | $3.38 | — | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-5-flash) |
| [Gemini 3.6 Flash](https://noometry.com/models/gemini-3-6-flash) | #33 | 54.1 | $1.50 | — | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-6-flash) |
| [GPT-5.2](https://noometry.com/models/gpt-5-2) | #34 | 54.1 | $4.81 | 15 | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-2) |
| [DeepSeek V4 Flash](https://noometry.com/models/deepseek-v4-flash) | #35 | 53.6 | $0.26 | 6 | [Compare](https://noometry.com/compare/deepseek-v4-flash-vs-deepseek-v4-pro) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

DeepSeek V4 Pro Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SWE-bench Verified](https://noometry.com/benchmarks/swe-bench-verified) | 77.6% | #6 of 32, top 19% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-18 |
| [FrontierCode](https://noometry.com/benchmarks/frontiercode) | 28.6% | #27 of 37, top 73% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [FrontierCode](https://noometry.com/benchmarks/frontiercode) | 17.6% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1464 |  |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1582 | #27 of 113, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1447 |  |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [SciCode](https://noometry.com/benchmarks/scicode) | 46.4% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 50% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 51% | #40 of 121, top 34% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 39.9% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 46.5% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 66.2% | #22 of 119, top 19% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 48.9% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1469 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1470 | #57 of 294, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1453 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 1,006 |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 1,403 | #19 of 105, top 19% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 521.67 |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Agentic & Tool Use

DeepSeek V4 Pro Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [APEX-Agents](https://noometry.com/benchmarks/apex-agents) | 47.3% | #29 of 49, top 60% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Vending-Bench 2](https://noometry.com/benchmarks/vending-bench-2) | 3,285 | #41 of 60, top 69% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

DeepSeek V4 Pro Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 59.7% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 56.3% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 61.3% | #26 of 83, top 32% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 0.8% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 53.5% | #54 of 99, top 55% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 67.3% |  |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 91.3% | #14 of 91, top 16% | high reasoning | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 87.2% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 90.5% | #25 of 83, top 31% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 90% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 13% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 10% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 12.9% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 18% | #29 of 134, top 22% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 0% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 13% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 47% | #13 of 129, top 11% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-18 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 20% |  | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-16 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 7% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1452 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1458 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1461 | #46 of 297, top 16% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 43% | #13 of 74, top 18% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-19 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 17% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 93.9% | #24 of 151, top 16% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 90.7% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 45.5% | #32 of 125, top 26% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 41.2% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Surface Evolver Bench](https://noometry.com/benchmarks/surface-evolver-bench) | 40% | #20 of 25, top 80% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 149.13 |  |  | [Epoch AI](https://epoch.ai/eci) | 2026-04-24 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 155.31 | #29 of 213, top 14% |  | [Epoch AI](https://epoch.ai/eci) | 2026-08-13 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 56.1 | #66 of 72, top 92% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

DeepSeek V4 Pro Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 45.3% |  | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-17 |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 64.6% | #32 of 81, top 40% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-19 |
| [FrontierMath Tier 4](https://noometry.com/benchmarks/frontiermath-tier-4) | 2.4% |  | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-17 |
| [FrontierMath Tier 4](https://noometry.com/benchmarks/frontiermath-tier-4) | 26.8% | #34 of 63, top 54% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-19 |
| [MathArena Final-Answer Competitions](https://noometry.com/benchmarks/matharena) | 76.6% | #7 of 29, top 25% | max | [MathArena](https://matharena.ai/) |  |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 95.6% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 96.7% |  | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-17 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 98.6% | #19 of 173, top 11% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-18 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 46.7% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 50% | #29 of 77, top 38% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 16% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1443 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1439 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1455 | #59 of 285, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

DeepSeek V4 Pro Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 90.9% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 91.7% | #24 of 186, top 13% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-18 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 89.6% |  | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-16 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 73.2% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 47% |  | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 52.9% | #21 of 77, top 28% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 8.6% | #40 of 96, top 42% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1464 | #57 of 273, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1458 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1449 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

DeepSeek V4 Pro Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1439 | #45 of 297, top 16% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1431 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1431 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1480 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1486 | #60 of 285, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1477 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1452 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1472 | #35 of 223, top 16% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1448 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1458 | #37 of 231, top 17% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1447 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1415 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1445 | #27 of 211, top 13% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1411 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1425 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1447 | #20 of 213, top 10% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1453 | #40 of 283, top 15% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1448 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1449 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1458 | #38 of 226, top 17% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1432 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1449 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

DeepSeek V4 Pro Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1445 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1448 | #43 of 298, top 15% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1436 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

DeepSeek V4 Pro Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [CL-bench Life](https://noometry.com/benchmarks/cl-bench-life) | 13.5% | #6 of 13, top 47% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1458 | #42 of 291, top 15% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1446 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1458 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

DeepSeek V4 Pro Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1445 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1446 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1451 | #41 of 297, top 14% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1446 | #31 of 295, top 11% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1441 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1438 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1553 | #50 of 115, top 44% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [EQ-Bench 4](https://noometry.com/benchmarks/eqbench-4) | 1166 | #18 of 28, top 65% |  | [EQ-Bench](https://eqbench.com/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1455 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1446 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1467 | #32 of 295, top 11% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

DeepSeek V4 Pro API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | $1.74 | $3.48 | — | 2026-10-10 |
| [deepinfra](https://deepinfra.com/models) | $1.30 | $2.60 | $0.10 | 2026-10-10 |
| [deepseek](https://api-docs.deepseek.com/quick_start/pricing) | $0.66 | $1.98 | $0.022 | 2026-10-10 |
| [openrouter](https://openrouter.ai/deepseek/deepseek-v4-pro) | $0.21 | $0.42 | $0.0174 | 2026-10-10 |
| [together](https://docs.together.ai/docs/serverless-models) | $1.32 | $3.96 | $0.13 | 2026-10-10 |

[All DeepSeek API prices →](https://noometry.com/llm-pricing/deepseek) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare DeepSeek V4 Pro

-   [DeepSeek V4 Pro vs GPT-5.6 Luna](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-6-luna)
-   [DeepSeek V4 Pro vs Gemini 3.5 Flash](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-5-flash)
-   [DeepSeek V4 Pro vs Claude Sonnet 5](https://noometry.com/compare/claude-sonnet-5-vs-deepseek-v4-pro)
-   [DeepSeek V4 Pro vs Gemini 3.6 Flash](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-6-flash)
-   [DeepSeek V4 Pro vs Gemini 3 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-pro)
-   [DeepSeek V4 Pro vs GPT-5.2](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-2)
-   [DeepSeek V4 Pro vs GPT-6 Astra](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-6-astra)
-   [DeepSeek V4 Pro vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-deepseek-v4-pro)
-   [DeepSeek V4 Pro vs Gemini 3.8 Flash](https://noometry.com/compare/deepseek-v4-pro-vs-gemini-3-8-flash)
-   [DeepSeek V4 Pro vs Kimi K3](https://noometry.com/compare/deepseek-v4-pro-vs-kimi-k3)
-   [DeepSeek V4 Pro vs Grok 4.6](https://noometry.com/compare/deepseek-v4-pro-vs-grok-4-6)
-   [DeepSeek V4 Pro vs Qwen3.8 Max](https://noometry.com/compare/deepseek-v4-pro-vs-qwen3-8-max)
-   [DeepSeek V4 Pro vs GLM-5.3](https://noometry.com/compare/deepseek-v4-pro-vs-glm-5-3)
-   [DeepSeek V4 Pro vs Muse Spark 1.3](https://noometry.com/compare/deepseek-v4-pro-vs-muse-spark-1-3)

## Other DeepSeek models

-   [DeepSeek V4 Flash](https://noometry.com/models/deepseek-v4-flash)53.6
-   [DeepSeek V4.1 Flash](https://noometry.com/models/deepseek-v4-1-flash)52.8
-   [DeepSeek-V3.2-Exp](https://noometry.com/models/deepseek-v3-2-exp)44.3
-   [DeepSeek-V3.1-Terminus](https://noometry.com/models/deepseek-v3-1-terminus)43.1
-   [DeepSeek-V3.1](https://noometry.com/models/deepseek-v3-1)42.8
-   [DeepSeek-R1](https://noometry.com/models/deepseek-r1)42.3
-   [DeepSeek-V3.2-Speciale](https://noometry.com/models/deepseek-v3-2-speciale)39.7
-   [DeepSeek-V3](https://noometry.com/models/deepseek-v3)39.5

## Frequently asked questions

### How good is DeepSeek V4 Pro?

DeepSeek V4 Pro by DeepSeek ranks 31st of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.3. Its strongest category is reasoning, where it ranks 24th. API pricing starts at $0.66 per million input tokens and $1.98 per million output tokens, with a 1M-token context window.

### How much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro costs $0.66 per million input tokens and $1.98 per million output tokens on DeepSeek's own API, with cached input at $0.022.

### What is DeepSeek V4 Pro's context window?

DeepSeek V4 Pro accepts up to 1M tokens of input and can write up to 393K tokens in one response.

### Is DeepSeek V4 Pro open source?

Yes. DeepSeek V4 Pro's weights are downloadable from Hugging Face (deepseek-ai/DeepSeek-V4-Pro); check the license for commercial terms.

### How fast is DeepSeek V4 Pro?

DeepSeek V4 Pro generated about 16 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are DeepSeek V4 Pro's strengths and weaknesses?

Relative to other ranked models, DeepSeek V4 Pro places best in reasoning, math, knowledge and lowest in agentic & tool use, long context, instruction following.

### What is DeepSeek V4 Pro best at?

Its best category is reasoning, where it ranks 24th on Noometry.

### Cite this page

Noometry. (2026). DeepSeek V4 Pro benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/deepseek-v4-pro

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/deepseek-v4-pro.md).