# DeepSeek V3 0324

DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 per million output tokens, as of October 22, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 35 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/deepseek-chat-v3-0324
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: DeepSeek
- Released: March 24, 2025
- Price per million input tokens: $0.27
- Price per million output tokens: $1.07
- Context window: 164K tokens

Benchmark results (35 of 195):

- SWE-bench Verified: 42.0% (source: SWE-bench (swebench.com), read October 22, 2026)
- GPQA Diamond: 61.6% (source: GPQA (Vals AI), read October 22, 2026)
- AIME: 52.2% (source: AIME (Vals AI), read October 22, 2026)
- MMLU Pro: 79.5% (source: MMLU Pro (Vals AI), read October 22, 2026)
- AA Intelligence Index: 9.7 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Coding Index: 21.2 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Agentic Index: 0.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- LiveCodeBench (Vals AI): 65.5% (source: Vals AI boards, read October 22, 2026)
- MATH 500 (Vals AI): 88.6% (source: Vals AI boards, read October 22, 2026)
- MGSM (Vals AI): 91.7% (source: Vals AI boards, read October 22, 2026)
- LegalBench (Vals AI): 77.7% (source: Vals AI boards, read October 22, 2026)
- CorpFin (Vals AI): 54.7% (source: Vals AI boards, read October 22, 2026)
- TaxEval (Vals AI): 71.1% (source: Vals AI boards, read October 22, 2026)
- MedQA (Vals AI): 82.0% (source: Vals AI boards, read October 22, 2026)
- AA Math Index: 41.0 (source: Artificial Analysis, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 65.5% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 4.7% (source: Artificial Analysis, read October 22, 2026)
- MMLU Pro (Artificial Analysis run): 81.9% (source: Artificial Analysis, read October 22, 2026)
- LiveCodeBench (Artificial Analysis run): 40.5% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 39.0% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 15.2% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 41.0% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 40.7% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 47.1% (source: Artificial Analysis, read October 22, 2026)
- AIME 2025 (Artificial Analysis run): 41.0% (source: Artificial Analysis, read October 22, 2026)
- WeirdML: 36.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- METR time horizons: 49.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 67.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleBench: 27.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 37.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- MATH level 5: 75.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DTBench: 64.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 15.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Fiction.LiveBench: 50.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Creative writing (Lech Mazur): 77.0% (source: Epoch AI benchmarking hub, read October 22, 2026)