Compare · ModelsLive · 2 picked · head to head

DeepSeek V4 Flash 0731 vs o3

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

DeepSeek V4 Flash 0731 wins 10 of 12 shared benchmarks. Leads in reasoning · general · math.

Category leads
reasoning·DeepSeek V4 Flash 0731knowledge·o3general·DeepSeek V4 Flash 0731math·DeepSeek V4 Flash 0731coding·DeepSeek V4 Flash 0731

Head to head · from the data · data as of 2026-11-22

  • Benchmarks · DeepSeek V4 Flash 0731 leads on 10 of 12 shared benchmarks (ARC-AGI, ARC-AGI-2, Dtbench, FrontierMath-Tiers-1-3-v2-Private, 6 more), o3 on 2 (Chess Puzzles, SimpleQA Verified)
  • Price · DeepSeek V4 Flash 0731 input $0.04/M vs o3 $2.00/M, DeepSeek V4 Flash 0731 is 98% cheaper (OpenRouter list price, as of 2026-11-22)
  • Cheapest provider · DeepSeek V4 Flash 0731 at Baidu $0.04/M input (of 26 offers) as of 2026-11-22 · o3 at OpenAI $2.00/M input (1 offer) as of 2026-11-22
  • Context · DeepSeek V4 Flash 0731 1.0M tokens vs o3 200K tokens
  • Released · DeepSeek V4 Flash 0731 Jul 31, 2026 vs o3 Apr 16, 2025 · 15 months apart
  • Price history · o3 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
DeepSeek V4 Flash 0731
#85 by perf·#4 by attention
DESERVED
o3
#124 by perf·no signal
QUIET
Best value
31.5x better value than o3
DeepSeek V4 Flash 0731
323.6 pts/$
$0.17/M
o3
10.3 pts/$
$5.00/M
Vendor risk
One or more vendors flagged
DeepSeek logo
DeepSeek
$3.4B·Tier 1
Higher risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
DeepSeek V4 Flash 0731o3
ARC-AGI
DeepSeek V4 Flash 0731 leads by +28.2
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
DeepSeek V4 Flash 0731
89.0
o3
60.8
ARC-AGI-2
DeepSeek V4 Flash 0731 leads by +54.9
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
DeepSeek V4 Flash 0731
61.4
o3
6.5
Chess Puzzles
o3 leads by +5.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V4 Flash 0731
28.4
o3
33.7
Dtbench
DeepSeek V4 Flash 0731 leads by +10.2
DeepSeek V4 Flash 0731
84.9
o3
74.7
FrontierMath-Tiers-1-3-v2-Private
DeepSeek V4 Flash 0731 leads by +25.5
DeepSeek V4 Flash 0731
60.6
o3
35.1
GPQA diamond
DeepSeek V4 Flash 0731 leads by +16.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V4 Flash 0731
91.7
o3
75.8
Lmca
DeepSeek V4 Flash 0731 leads by +2.4
DeepSeek V4 Flash 0731
49.1
o3
46.7
Mystery Game Puzzles
DeepSeek V4 Flash 0731 leads by +5.5
DeepSeek V4 Flash 0731
27.3
o3
21.8
OTIS Mock AIME 2024-2025
DeepSeek V4 Flash 0731 leads by +10.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4 Flash 0731
94.4
o3
84.4
SimpleBench
DeepSeek V4 Flash 0731 leads by +9.6
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
DeepSeek V4 Flash 0731
53.3
o3
43.7
SimpleQA Verified
o3 leads by +19.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
DeepSeek V4 Flash 0731
33.6
o3
53.0
WeirdML
DeepSeek V4 Flash 0731 leads by +10.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V4 Flash 0731
63.0
o3
52.4
Full benchmark table
BenchmarkDeepSeek V4 Flash 0731o3
ARC-AGI
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
89.060.8
ARC-AGI-2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
61.46.5
Chess Puzzles
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
28.433.7
Dtbench
84.974.7
FrontierMath-Tiers-1-3-v2-Private
60.635.1
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
91.775.8
Lmca
49.146.7
Mystery Game Puzzles
27.321.8
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
94.484.4
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
53.343.7
SimpleQA Verified
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
33.653.0
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
63.052.4
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
DeepSeek logoDeepSeek V4 Flash 0731$0.04$0.301.0M tokens (~524 books)$1.08
OpenAI logoo3$2.00$8.00200K tokens (~100 books)$35.00
DeepSeek V4 Flash 0731 leads on 10 of 12 shared benchmarks (ARC-AGI, ARC-AGI-2, Dtbench, FrontierMath-Tiers-1-3-v2-Private, 6 more), o3 on 2 (Chess Puzzles, SimpleQA Verified)