Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Flash 0731 vs GPT-4.1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Flash 0731 wins on 11/11 benchmarks
DeepSeek V4 Flash 0731 wins 11 of 11 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·DeepSeek V4 Flash 0731knowledge·DeepSeek V4 Flash 0731general·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-4.1
#189 by perf·no signal
Best value
DeepSeek V4 Flash 0731
10.8x better value than GPT-4.1
DeepSeek V4 Flash 0731
85.5 pts/$
$0.65/M
GPT-4.1
7.9 pts/$
$5.00/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
11 benchmarks · 2 models
DeepSeek V4 Flash 0731GPT-4.1
ARC-AGI
DeepSeek V4 Flash 0731 leads by +83.5
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-4.1
5.5
ARC-AGI-2
DeepSeek V4 Flash 0731 leads by +61.0
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-4.1
0.4
Chess Puzzles
DeepSeek V4 Flash 0731 leads by +28.4
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-4.1
1.1
Dtbench
DeepSeek V4 Flash 0731 leads by +37.8
DeepSeek V4 Flash 0731
84.9
GPT-4.1
47.1
FrontierMath-Tiers-1-3-v2-Private
DeepSeek V4 Flash 0731 leads by +51.6
DeepSeek V4 Flash 0731
57.5
GPT-4.1
6.0
GPQA diamond
DeepSeek V4 Flash 0731 leads by +32.2
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-4.1
55.9
Lmca
DeepSeek V4 Flash 0731 leads by +19.0
DeepSeek V4 Flash 0731
49.1
GPT-4.1
30.1
OTIS Mock AIME 2024-2025
DeepSeek V4 Flash 0731 leads by +56.2
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4 Flash 0731
94.4
GPT-4.1
38.3
SimpleBench
DeepSeek V4 Flash 0731 leads by +40.9
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-4.1
12.4
SimpleQA Verified
DeepSeek V4 Flash 0731 leads by +2.5
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-4.1
31.1
WeirdML
DeepSeek V4 Flash 0731 leads by +23.9
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-4.1
39.0
Full benchmark table
| Benchmark | DeepSeek V4 Flash 0731 | GPT-4.1 |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 89.0 | 5.5 |
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 | 0.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 29.5 | 1.1 |
Dtbench | 84.9 | 47.1 |
FrontierMath-Tiers-1-3-v2-Private | 57.5 | 6.0 |
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 | 55.9 |
Lmca | 49.1 | 30.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.4 | 38.3 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 53.3 | 12.4 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 33.6 | 31.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 63.0 | 39.0 |
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 | |
| $2.00 | $8.00 | 1.0M tokens (~524 books) | $35.00 |