AI models

DeepSeek V4 Pro vs Qwen3.8 Max

Same criteria, side by side. Where the gap is small, it may be measurement noise.

DeepSeek V4 Pro

US$ 1.32 / US$ 3.96 peak hours

Input US$/1M / Output US$/1M · Official pricing

Qwen3.8 Max

US$ 2.00 / US$ 6.00

Input US$/1M / Output US$/1M · Official pricing

GPQA Diamond

90.9% · 92.3%

DeepSeek V4 Pro · Qwen3.8 Max

01

Direct answer

Direct answer: GPQA Diamond: DeepSeek V4 Pro 90.9%, Qwen3.8 Max 92.3% (Epoch AI). FrontierMath (tiers 1 to 3): DeepSeek V4 Pro 45.3%, Qwen3.8 Max 65.6% (Epoch AI). SimpleQA Verified: DeepSeek V4 Pro 47%, Qwen3.8 Max 47.3% (Epoch AI).
see more

02

Pick Qwen3.8 Max if scores come first: it leads on GPQA Diamond and FrontierMath and is in a statistical tie with DeepSeek V4 Pro on SimpleQA Verified. Pick DeepSeek V4 Pro if cost matters more: at official prices it charges US$ 1.32 versus US$ 2.00 per 1M input tokens and US$ 3.96 versus US$ 6.00 per 1M output.

Qwen3.8 Max

  • GPQA Diamond +1.4 p.p.
  • FrontierMath +20.3 p.p.

statistical tie

  • SimpleQA Verified statistical tie

03

MetricDeepSeek V4 ProQwen3.8 MaxSource
Input US$/1MUS$ 1.32 / US$ 3.96 Official pricing peak hoursUS$ 2.00 / US$ 6.00 Official pricing
Output US$/1MUS$ 3.96US$ 6.00
Context1,048,5761,000,000
BENCHMARKS
GPQA Diamond90.9%between 34th and 60th of 250 92.3%between 25th and 37th of 250 Epoch AI
OTIS Mock AIME saturated96.7% statistical tie with the top score100% top scoreEpoch AI
FrontierMath (tiers 1 to 3)45.3%between 56th and 58th of 85 65.6%between 36th and 40th of 85 Epoch AI
SimpleQA Verified statistical tie47%between 36th and 41st of 87 statistical tie47.3%between 35th and 41st of 87 statistical tieEpoch AI
OTIS Mock AIME saturated96.7% statistical tie with the top score100% top scoreEpoch AI

04

Compare with

05

Sources

  • Epoch AI, CC BY 4.0, latest version we checked.
  • OpenRouter Benchmarks, CC BY 4.0, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.

How to cite

If you use this data, cite the page and the date you accessed it.

Adriano Meirinho. "DeepSeek V4 Pro vs Qwen3.8 Max". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/comparar/deepseek-v4-pro-vs-qwen3-8-max/. Accessed November 21, 2026.

Third-party data follows the license of each source. The full table is available as CSV and JSON.

Markdown