Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Flash 0731 vs GPT-5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Flash 0731 wins on 12/14 benchmarks
DeepSeek V4 Flash 0731 wins 12 of 14 shared benchmarks. Leads in reasoning · general · math.
Category leads
reasoning·DeepSeek V4 Flash 0731knowledge·GPT-5general·DeepSeek V4 Flash 0731math·DeepSeek V4 Flash 0731coding·DeepSeek V4 Flash 0731
Hype vs Reality
Attention vs performance
DeepSeek V4 Flash 0731
#76 by perf·#6 by attention
GPT-5
#100 by perf·#4 by attention
Best value
DeepSeek V4 Flash 0731
9.1x better value than GPT-5
DeepSeek V4 Flash 0731
85.5 pts/$
$0.65/M
GPT-5
9.4 pts/$
$5.63/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
14 benchmarks · 2 models
DeepSeek V4 Flash 0731GPT-5
ARC-AGI
DeepSeek V4 Flash 0731 leads by +23.3
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
GPT-5
65.7
ARC-AGI-2
DeepSeek V4 Flash 0731 leads by +51.5
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
GPT-5
9.9
Chess Puzzles
GPT-5 leads by +4.2
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V4 Flash 0731
29.5
GPT-5
33.7
Dtbench
DeepSeek V4 Flash 0731 leads by +0.4
DeepSeek V4 Flash 0731
84.9
GPT-5
84.5
FrontierMath-Tier-4-v2-Private
DeepSeek V4 Flash 0731 leads by +2.4
DeepSeek V4 Flash 0731
24.4
GPT-5
21.9
FrontierMath-Tiers-1-3-v2-Private
DeepSeek V4 Flash 0731 leads by +2.1
DeepSeek V4 Flash 0731
57.5
GPT-5
55.4
GPQA diamond
DeepSeek V4 Flash 0731 leads by +6.5
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
88.0
GPT-5
81.6
Lmca
DeepSeek V4 Flash 0731 leads by +2.0
DeepSeek V4 Flash 0731
49.1
GPT-5
47.0
Mystery Game Puzzles
DeepSeek V4 Flash 0731 leads by +12.1
DeepSeek V4 Flash 0731
27.3
GPT-5
15.2
OTIS Mock AIME 2024-2025
DeepSeek V4 Flash 0731 leads by +3.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4 Flash 0731
94.4
GPT-5
91.4
Proofbench
DeepSeek V4 Flash 0731 leads by +38.0
DeepSeek V4 Flash 0731
56.0
GPT-5
18.0
SimpleBench
DeepSeek V4 Flash 0731 leads by +5.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
DeepSeek V4 Flash 0731
53.3
GPT-5
48.0
SimpleQA Verified
GPT-5 leads by +16.5
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
GPT-5
50.1
WeirdML
DeepSeek V4 Flash 0731 leads by +2.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V4 Flash 0731
63.0
GPT-5
60.7
Full benchmark table
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5 |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 89.0 | 65.7 |
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. | 61.4 | 9.9 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 29.5 | 33.7 |
Dtbench | 84.9 | 84.5 |
FrontierMath-Tier-4-v2-Private | 24.4 | 21.9 |
FrontierMath-Tiers-1-3-v2-Private | 57.5 | 55.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 88.0 | 81.6 |
Lmca | 49.1 | 47.0 |
Mystery Game Puzzles | 27.3 | 15.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.4 | 91.4 |
Proofbench | 56.0 | 18.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 53.3 | 48.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 33.6 | 50.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 63.0 | 60.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.02 | $1.28 | 1.0M tokens (~524 books) | $3.31 | |
| $1.25 | $10.00 | 400K tokens (~200 books) | $34.38 |