# DeepSeek V3

DeepSeek · Open Weight · rank 174 · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/models/deepseek-v3  
JSON: https://modelscale.dev/api/model/deepseek-v3

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `deepseek-v3` | — |
| Overall score | 37.2 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 42 | Observed 2026-11-21 · source benchlm:models |
| Context window | 128K tokens | Observed 2026-11-21 · source benchlm:models |
| Release date | 2024-12-26 | Observed 2026-11-21 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | $0.48 | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Coding | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Knowledge | 37.4 | Observed 2026-11-21 · source benchlm:models | 37.4 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 26.2 | Observed 2026-11-21 · source benchlm:models | 26.2 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | 39.6 | Observed 2026-11-21 · source benchlm:models | 39.6 | Observed 2026-11-21 · source benchlm:models |
| Math | 26 | Last good 2026-10-08 · source benchlm:models | 26 | Last good 2026-10-08 · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 1.25 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 37 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $0.27 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $1.10 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | $0.07 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $0.48 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |

**Pricing note.** DeepSeek's official DeepSeek-V3 launch page lists $0.27 input (cache miss) / $1.10 output per million tokens, with cache-hit input at $0.07.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $1.34 |
| Modelled tokens | 2.82M |

## Benchmark record

26 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 59.1 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| MMLU-Pro (Massive Multitask Language Understanding Professional) | 75.9 | Multiple subjects | Professional level | [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://arxiv.org/abs/2406.01574) |
| Artificial Analysis Intelligence Index | 8.5 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 55.7 | Graduate-level science questions | Graduate-level science reasoning | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 2.9 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | -41.6 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 25.5 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 90.0 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| SimpleQA (Measuring Short-Form Factuality in Large Language Models) | 24.9 | Factual questions | Factual accuracy focused | [Measuring short-form factuality in large language models](https://arxiv.org/abs/2411.04368) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 42 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| LiveCodeBench (LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code) | 37.6 | Continuously updated contest problems | Competitive programming level | [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://arxiv.org/abs/2403.07974) |
| AA Coding Index (Artificial Analysis Coding Index) | 23.0 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 35.8 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AIME 2024 (American Invitational Mathematics Examination 2024) | 39.2 | 15 problems | High school olympiad level | [American Invitational Mathematics Examination](https://www.maa.org/math-competitions/aime) |
| MATH-500 (MATH-500 Problem Set) | 90.2 | 500 problems | High school to undergraduate | [Measuring Mathematical Problem Solving With the MATH Dataset](https://arxiv.org/abs/2103.03874) |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 1.724 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| LongBench v2 | 48.7 | Long-context tasks | Hard long-context | [LongBench v2](https://arxiv.org/abs/2412.15204) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 29.3 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| CritPt (Critical Physics Tasks) | 0.0 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| IFEval (Instruction-Following Eval) | 86.1 | 541 prompts across 25 instruction types | Instruction precision | [Instruction-Following Evaluation for Large Language Models](https://arxiv.org/abs/2311.07911) |
| AA-IFBench (Artificial Analysis IFBench) | 34.8 | Verifiable instruction constraints | Instruction precision | [Artificial Analysis IFBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/ifbench) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GDPval-AA | 183 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 0.0 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 0.8 | Cross-benchmark agentic index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| τ²-bench results (τ²-Bench Tool-Agent-User Evaluation) | 22.8 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | [τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Design Arena Website (Design Arena Website Elo) | 1109 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

## Independent scores (Epoch AI)

A second, independent score source: Epoch's own figures in Epoch's units, one line per model version Epoch evaluated (effort setting as Epoch labels it); higher is better. Not part of this site's capability scores or rank.

| Benchmark | Variant | Score | Unit | Epoch date | Evidence |
| --- | --- | --- | --- | --- | --- |
| GPQA Diamond | default | 0.5653 | fraction (0–1) | 2025-01-27 | Last good 2026-11-20 · source epoch:benchmarks |
| Aider polyglot | default (diff) | 48.4% | percent | — | Last good 2026-11-20 · source epoch:benchmarks |
| METR time horizon | default (METR version not stated) | 18.5 min | minutes | — | Last good 2026-11-20 · source epoch:benchmarks |

Source: [Epoch AI, CC BY 4.0](https://epoch.ai/benchmarks) ([licence](https://creativecommons.org/licenses/by/4.0/)). Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-11-21 01:17 UTC.
