Compare · ModelsLive · 2 picked · head to head
R1 0528 vs DeepSeek V4 Pro 0813
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Pro 0813 wins on 6/7 benchmarks
DeepSeek V4 Pro 0813 wins 6 of 7 shared benchmarks. Leads in reasoning · knowledge · math.
Category leads
speed·R1 0528reasoning·DeepSeek V4 Pro 0813knowledge·DeepSeek V4 Pro 0813math·DeepSeek V4 Pro 0813coding·DeepSeek V4 Pro 0813
Hype vs Reality
Attention vs performance
R1 0528
#60 by perf·#17 by attention
DeepSeek V4 Pro 0813
#50 by perf·#7 by attention
Best value
DeepSeek V4 Pro 0813
1.0x better value than R1 0528
R1 0528
43.7 pts/$
$1.32/M
DeepSeek V4 Pro 0813
45.5 pts/$
$1.32/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
DeepSeek
$3.4B·Tier 1
Head to head
7 benchmarks · 2 models
R1 0528DeepSeek V4 Pro 0813
Artificial Analysis · Quality Index
R1 0528 leads by +6.7
R1 0528
27.1
DeepSeek V4 Pro 0813
20.4
ARC-AGI
DeepSeek V4 Pro 0813 leads by +69.3
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
R1 0528
21.2
DeepSeek V4 Pro 0813
90.5
ARC-AGI-2
DeepSeek V4 Pro 0813 leads by +60.1
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
R1 0528
1.1
DeepSeek V4 Pro 0813
61.3
GPQA diamond
DeepSeek V4 Pro 0813 leads by +20.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
R1 0528
68.4
DeepSeek V4 Pro 0813
88.9
OTIS Mock AIME 2024-2025
DeepSeek V4 Pro 0813 leads by +32.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
R1 0528
66.4
DeepSeek V4 Pro 0813
98.6
SimpleQA Verified
DeepSeek V4 Pro 0813 leads by +25.5
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
R1 0528
27.4
DeepSeek V4 Pro 0813
52.9
WeirdML
DeepSeek V4 Pro 0813 leads by +24.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
R1 0528
41.6
DeepSeek V4 Pro 0813
66.2
Full benchmark table
| Benchmark | R1 0528 | DeepSeek V4 Pro 0813 |
|---|---|---|
Artificial Analysis · Quality Index | 27.1 | 20.4 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 21.2 | 90.5 |
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. | 1.1 | 61.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 68.4 | 88.9 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 66.4 | 98.6 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 27.4 | 52.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 41.6 | 66.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.50 | $2.15 | 164K tokens (~82 books) | $9.13 | |
| $0.66 | $1.98 | 1.0M tokens (~524 books) | $9.90 |