# DeepSeek V3.1 Terminus

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 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 45 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/deepseek-v3-1-terminus
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: DeepSeek
- Released: September 22, 2025
- Price per million input tokens: $0.3063
- Price per million output tokens: $1.0142
- Context window: 164K tokens

Benchmark results (45 of 195):

- AA Intelligence Index: 14.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Coding Index: 43.5 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Agentic Index: 6.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1187 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1182 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1131 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 1168 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1141 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1175 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: SVG: 1065 Elo (source: Design Arena, read October 22, 2026)
- AA Math Index: 89.7 (source: Artificial Analysis, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 79.2% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 16.4% (source: Artificial Analysis, read October 22, 2026)
- MMLU Pro (Artificial Analysis run): 85.1% (source: Artificial Analysis, read October 22, 2026)
- LiveCodeBench (Artificial Analysis run): 79.8% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 38.0% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 31.8% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 57.0% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 69.3% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 37.1% (source: Artificial Analysis, read October 22, 2026)
- AIME 2025 (Artificial Analysis run): 89.7% (source: Artificial Analysis, read October 22, 2026)
- DTBench: 81.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 28.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ALE-Bench: 745.2 (source: ALE-Bench (Sakana AI), read October 22, 2026)
- LMArena Text: 1419 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1425 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1426 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1402 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1404 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1403 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1429 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1408 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1435 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1427 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1411 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1422 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1432 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1426 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1451 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1468 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1457 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1414 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1409 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1391 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- Kagi LLM Benchmark: 57.4% (source: Kagi LLM Benchmarking Project, read October 22, 2026)