Artificial Analysis · Intelligence Index · Reasoning14.8304thof 696 models
Coding index43.5 · 132nd
Math index89.7 · 26th
Benchmarks, as Artificial Analysis ran them- 79%GPQA Diamond
- 16%Humanity's Last Exam
- 0%Terminal-Bench 4.0
- 45%Terminal-Bench 2.1
- 30%Terminal-Bench Hard
- 80%LiveCodeBench
- 90%AIME 2025
- 38%SciCode
- 37%τ²-Bench
- 21%τ²-Bench Banking
- 85%MMLU-Pro
- 57%IFBench
- 69%Long context reasoning
- Per 1M tokens
- $1.64 in · $2.75 out
- Context
- 164K tokens
LMArena141stof 416· 47th of 226 open models
Against list priceRating for the price
DeepSeek-V3.1-Terminus · 1,415 · $0.45 per 1M tokens ($0.27 in, $1.00 out) · 164K context
DeepSeek-V3.1-Terminus · 1,415 · $0.45 per 1M tokens ($0.27 in, $1.00 out) · 164K context
LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 20 October 2026 · Artificial Analysis, read 20 October 2026
DeepSeek-V3.1-Terminus