DeepSeek, open weights

# DeepSeek-V2.5 (Sep 2024)

> DeepSeek-V2.5 (Sep 2024) by DeepSeek, released September 2024. Ranked #200 of 354 with a Noometry Index of 37.6. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/deepseek-v2-5
- Last updated: 2026-10-10
- Title: DeepSeek-V2.5 (Sep 2024) Benchmarks, Price & Rank (October 2026)

DeepSeek-V2.5 (Sep 2024) by DeepSeek ranks 200th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.6. Its strongest category is reasoning, where it ranks 145th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #200 of 354
- **Index score:** 37.6
- **Evidence:** Confirmed 22 results
- **Provider:** [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek)
- **Released:** September 6, 2024
- **Weights:** Open weights
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** Not measured
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

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

DeepSeek-V2.5 (Sep 2024) category scores

1.  Coding 31.7
2.  Reasoning 25.6
3.  Math 35.9
4.  Knowledge 34.8
5.  Multilingual 42.5
6.  Instruction Following 67.5
7.  Long Context 39.5
8.  Writing & Preference 49.8
9.  020406080

DeepSeek-V2.5 (Sep 2024) category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 31.7 | #281 | 4 |
| [Reasoning](https://noometry.com/best/reasoning) | 25.6 | #145 | 1 |
| [Math](https://noometry.com/best/math) | 35.9 | #177 | 1 |
| [Knowledge](https://noometry.com/best/knowledge) | 34.8 | #193 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 42.5 | #193 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 67.5 | #194 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 39.5 | #174 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 49.8 | #187 | 3 |

## Strengths and weaknesses

Categories where DeepSeek-V2.5 (Sep 2024) places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

DeepSeek-V2.5 (Sep 2024): strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 25.6 | +2.0 | #145 of 350, top 42% |
| [Math](https://noometry.com/best/math) | 35.9 | −0.6 | #177 of 327, top 55% |
| [Long Context](https://noometry.com/best/long-context) | 39.5 | −1.4 | #174 of 296, top 59% |

### Weakest categories

DeepSeek-V2.5 (Sep 2024): weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 31.7 | −7.0 | #281 of 340, top 83% |
| [Multilingual](https://noometry.com/best/multilingual) | 42.5 | −4.9 | #193 of 297, top 65% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 67.5 | −3.8 | #194 of 305, top 64% |

## Closest competitors

The models ranked just above and below DeepSeek-V2.5 (Sep 2024). When scores are this close, price and speed are often the better way to choose.

Models ranked closest to DeepSeek-V2.5 (Sep 2024)
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [MiniMax-M2.7](https://noometry.com/models/minimax-m2-7) | #196 | 37.7 | $0.52 | — | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-minimax-m2-7) |
| [Gemini Advanced 0514](https://noometry.com/models/gemini-advanced) | #197 | 37.7 | — | — | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-gemini-advanced) |
| [Grok 2 Mini 2024 08 13](https://noometry.com/models/grok-2-mini) | #198 | 37.7 | — | — | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-grok-2-mini) |
| [Mercury](https://noometry.com/models/mercury) | #199 | 37.6 | — | 35 | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-mercury) |
| [Qwen3.6 35B-A3B](https://noometry.com/models/qwen3-6-35b-a3b) | #201 | 37.6 | $0.56 | — | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-qwen3-6-35b-a3b) |
| [Hunyuan Large Vision](https://noometry.com/models/hunyuan-large-vision) | #202 | 37.6 | — | — | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-hunyuan-large-vision) |
| [Llama 3.1 Nemotron 70b Instruct](https://noometry.com/models/llama-3-1-nemotron-70b-instruct) | #203 | 37.6 | — | — | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-llama-3-1-nemotron-70b-instruct) |
| [MiniMax-M2](https://noometry.com/models/minimax-m2) | #204 | 37.4 | $0.52 | 17 | [Compare](https://noometry.com/compare/deepseek-v2-5-vs-minimax-m2) |

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-V2.5 (Sep 2024) Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 17.8% | #36 of 44, top 82% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 48.6% | #7 of 64, top 11% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-12-10 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1301 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1309 | #192 of 294, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 53.2% | #25 of 66, top 38% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-12-10 |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 83.5% | #7 of 45, top 16% | nov 2024 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 74.1% | #7 of 38, top 19% | nov 2024 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Reasoning

DeepSeek-V2.5 (Sep 2024) Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1289 | #193 of 297, top 65% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1270 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

DeepSeek-V2.5 (Sep 2024) Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1271 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1288 | #187 of 285, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

DeepSeek-V2.5 (Sep 2024) Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1266 | #188 of 273, top 69% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1240 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

DeepSeek-V2.5 (Sep 2024) Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1273 | #193 of 297, top 65% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1253 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1281 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1318 | #182 of 285, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1289 | #166 of 223, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1258 | #172 of 231, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1226 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1228 | #147 of 211, top 70% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1190 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1209 | #155 of 213, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1253 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1289 | #181 of 283, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1248 | #183 of 226, top 81% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

DeepSeek-V2.5 (Sep 2024) Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1280 | #187 of 298, top 63% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1249 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

DeepSeek-V2.5 (Sep 2024) Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1273 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1301 | #187 of 291, top 65% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

DeepSeek-V2.5 (Sep 2024) Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1294 | #194 of 297, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1271 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1237 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1285 | #183 of 295, top 63% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1261 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1297 | #190 of 295, top 65% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare DeepSeek-V2.5 (Sep 2024)

-   [DeepSeek-V2.5 (Sep 2024) vs Mercury](https://noometry.com/compare/deepseek-v2-5-vs-mercury)
-   [DeepSeek-V2.5 (Sep 2024) vs Qwen3.6 35B-A3B](https://noometry.com/compare/deepseek-v2-5-vs-qwen3-6-35b-a3b)
-   [DeepSeek-V2.5 (Sep 2024) vs Grok 2 Mini 2024 08 13](https://noometry.com/compare/deepseek-v2-5-vs-grok-2-mini)
-   [DeepSeek-V2.5 (Sep 2024) vs Hunyuan Large Vision](https://noometry.com/compare/deepseek-v2-5-vs-hunyuan-large-vision)
-   [DeepSeek-V2.5 (Sep 2024) vs Gemini Advanced 0514](https://noometry.com/compare/deepseek-v2-5-vs-gemini-advanced)
-   [DeepSeek-V2.5 (Sep 2024) vs Llama 3.1 Nemotron 70b Instruct](https://noometry.com/compare/deepseek-v2-5-vs-llama-3-1-nemotron-70b-instruct)
-   [DeepSeek-V2.5 (Sep 2024) vs GPT-6 Astra](https://noometry.com/compare/deepseek-v2-5-vs-gpt-6-astra)
-   [DeepSeek-V2.5 (Sep 2024) vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-deepseek-v2-5)
-   [DeepSeek-V2.5 (Sep 2024) vs Gemini 3.8 Flash](https://noometry.com/compare/deepseek-v2-5-vs-gemini-3-8-flash)
-   [DeepSeek-V2.5 (Sep 2024) vs Kimi K3](https://noometry.com/compare/deepseek-v2-5-vs-kimi-k3)
-   [DeepSeek-V2.5 (Sep 2024) vs Grok 4.6](https://noometry.com/compare/deepseek-v2-5-vs-grok-4-6)
-   [DeepSeek-V2.5 (Sep 2024) vs Qwen3.8 Max](https://noometry.com/compare/deepseek-v2-5-vs-qwen3-8-max)
-   [DeepSeek-V2.5 (Sep 2024) vs GLM-5.3](https://noometry.com/compare/deepseek-v2-5-vs-glm-5-3)
-   [DeepSeek-V2.5 (Sep 2024) vs Muse Spark 1.3](https://noometry.com/compare/deepseek-v2-5-vs-muse-spark-1-3)

## Other DeepSeek models

-   [DeepSeek V4 Pro](https://noometry.com/models/deepseek-v4-pro)54.3
-   [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

## Frequently asked questions

### How good is DeepSeek-V2.5 (Sep 2024)?

DeepSeek-V2.5 (Sep 2024) by DeepSeek ranks 200th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.6. Its strongest category is reasoning, where it ranks 145th.

### Is DeepSeek-V2.5 (Sep 2024) open source?

Yes. DeepSeek-V2.5 (Sep 2024)'s weights are downloadable; check the license for commercial terms.

### What are DeepSeek-V2.5 (Sep 2024)'s strengths and weaknesses?

Relative to other ranked models, DeepSeek-V2.5 (Sep 2024) places best in reasoning, math, long context and lowest in coding, multilingual, instruction following.

### What is DeepSeek-V2.5 (Sep 2024) best at?

Its best category is reasoning, where it ranks 145th on Noometry.

### Cite this page

Noometry. (2026). DeepSeek-V2.5 (Sep 2024) benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/deepseek-v2-5

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/deepseek-v2-5.md).