Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d257Policy30d64, 14 pendingSources1,010

DeepSeek-R1 vs Qwen3 235B A22B

DeepSeek · released

Wins 1 of 6 areas

Long documents

Alibaba · released

Wins 3 of 6 areas

Agents · Reasoning · Facts

Qwen3 235B A22B wins more areas, narrowly.DeepSeek-R1 is better at long documents.

Scores updated · 37 tests both models report · How we compare

Where each one wins

Tests won in each of the six 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.

Agents rests on a single test.

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-R1$2.00 to read · $4.00 to write$6.00Price from Artificial Analysis
Qwen3 235B A22B$0.70 to read · $2.80 to write$3.50Price from Alibaba's own price page

Qwen3 235B A22B costs 42% less for the same work.

The biggest differences

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

Where Qwen3 235B A22B pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.7points aheadQwen3 235B A22B22.4DeepSeek-R19.7
  • Very hard expert questions across many subjectsHumanity's Last Exam+2.5points aheadQwen3 235B A22B11DeepSeek-R18.5
  • Code for real scientific research problemsSciCode+1.6points aheadQwen3 235B A22B39.9DeepSeek-R138.3

Where DeepSeek-R1 pulls ahead

  • Fixes real GitHub issues in Python projectsSWE-bench Verified+14.8points aheadDeepSeek-R149.2Qwen3 235B A22B34.4
  • Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+12points aheadDeepSeek-R130.5Qwen3 235B A22B18.5
  • Questions about very long textsLongBench v2+8.2points aheadDeepSeek-R158.3Qwen3 235B A22B50.1

Every test, side by side

All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingEven

Full coding ranking

AgentsQwen3 235B A22B
  • GDPValQwen3 235B A22B by 11.8011.8+11.8

Full agents ranking

ReasoningQwen3 235B A22B

Full reasoning ranking

FactsQwen3 235B A22B

Full facts ranking

Long documentsDeepSeek-R1

Full long documents ranking

Following instructionsEven

Full following instructions ranking

Other results23 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-R1 or Qwen3 235B A22B?

Qwen3 235B A22B wins three of the six areas where both have results: agents, reasoning and facts. DeepSeek-R1 wins long documents. They are level on coding and following instructions.

Which is better for coding?

Neither. They win 1 coding test each of the 3 both models report, and 1 is a tie.

Which is cheaper?

DeepSeek-R1 costs $2.00 per million input tokens and $4.00 per million output tokens; Qwen3 235B A22B costs $0.70 and $2.80. That makes Qwen3 235B A22B about 42% cheaper for the same work.

How do you compare the two?

We use the 37 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 23 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.