Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

DeepSeek-V4-Pro vs Qwen3.5 397B A17B

DeepSeek · released

Wins 5 of 7 areas

Coding · Agents · Reasoning · Facts · Math

Alibaba · released

Wins 2 of 7 areas

Long documents · Following instructions

DeepSeek-V4-Pro is the stronger all-rounder.Qwen3.5 397B A17B is better at long documents.

Scores updated · 65 tests both models report · How we compare

Where each one wins

Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

Long documents and following instructions rest on a single test each.

What it costs

Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.

DeepSeek-V4-Pro$0.43 to read · $0.87 to write$1.30Price from Artificial Analysis
Qwen3.5 397B A17B$0.60 to read · $3.60 to write$4.20Price from Artificial Analysis

DeepSeek-V4-Pro costs 69% less for the same work.

The biggest differences

The three tests each model wins by the widest margin. Scores are out of 100.

Where DeepSeek-V4-Pro pulls ahead

  • Proof problems from the US Math OlympiadUSAMO 2026+24.4points aheadDeepSeek-V4-Pro60.7Qwen3.5 397B A17B36.3
  • Short factual questions, answered correctlySimpleQA Verified+20.2points aheadDeepSeek-V4-Pro46.2Qwen3.5 397B A17B26
  • Real work tasks from 44 professionsGDPVal+18.1points aheadDeepSeek-V4-Pro32.9Qwen3.5 397B A17B14.8

Where Qwen3.5 397B A17B pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.2points aheadQwen3.5 397B A17B11.1DeepSeek-V4-Pro5.9
  • Reasons across sets of long documentsAA-LCR+2.6points aheadQwen3.5 397B A17B77.3DeepSeek-V4-Pro74.7
  • Follows unfamiliar, precisely checkable instructionsIFBench+2.3points aheadQwen3.5 397B A17B78.8DeepSeek-V4-Pro76.5

Every test, side by side

All 65 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-V4-Pro

Full coding ranking

AgentsDeepSeek-V4-Pro

Full agents ranking

ReasoningDeepSeek-V4-Pro

Full reasoning ranking

FactsDeepSeek-V4-Pro

Full facts ranking

MathDeepSeek-V4-Pro

Full math ranking

Long documentsQwen3.5 397B A17B
  • AA-LCRQwen3.5 397B A17B by 2.674.777.3+2.6

Full long documents ranking

Following instructionsQwen3.5 397B A17B
  • IFBenchQwen3.5 397B A17B by 2.376.578.8+2.3

Full following instructions ranking

Other results38 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

Questions people ask

Which is better, DeepSeek-V4-Pro or Qwen3.5 397B A17B?

DeepSeek-V4-Pro wins five of the seven areas where both have results: coding, agents, reasoning, facts and math. Qwen3.5 397B A17B wins long documents and following instructions.

Which is better for coding?

DeepSeek-V4-Pro. It wins 8 of the 8 coding tests both models report; Qwen3.5 397B A17B wins none.

Which is cheaper?

DeepSeek-V4-Pro costs $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes DeepSeek-V4-Pro about 69% cheaper for the same work.

How do you compare the two?

We use the 65 benchmark tests both models have published scores on. The verdict counts the 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 38 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.

Compare DeepSeek-V4-Pro with

DeepSeek

Across the field

Compare Qwen3.5 397B A17B with

Alibaba

Across the field

All comparisons