Compare · ModelsLive · 2 picked · head to head
DeepSeek V4.1 Flash vs GPT-5 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4.1 Flash wins on 12/12 benchmarks
DeepSeek V4.1 Flash wins 12 of 12 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·DeepSeek V4.1 Flashknowledge·DeepSeek V4.1 Flashgeneral·DeepSeek V4.1 Flashmath·DeepSeek V4.1 Flash
Hype vs Reality
Attention vs performance
DeepSeek V4.1 Flash
#97 by perf·#4 by attention
GPT-5 Mini
#120 by perf·#9 by attention
Best value
DeepSeek V4.1 Flash
3.8x better value than GPT-5 Mini
DeepSeek V4.1 Flash
175.1 pts/$
$0.31/M
GPT-5 Mini
45.8 pts/$
$1.13/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
12 benchmarks · 2 models
DeepSeek V4.1 FlashGPT-5 Mini
ARC-AGI
DeepSeek V4.1 Flash leads by +40.2
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
DeepSeek V4.1 Flash
94.5
GPT-5 Mini
54.3
ARC-AGI-2
DeepSeek V4.1 Flash leads by +68.5
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
DeepSeek V4.1 Flash
72.9
GPT-5 Mini
4.4
Chess Puzzles
DeepSeek V4.1 Flash leads by +25.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V4.1 Flash
45.3
GPT-5 Mini
20.0
Dtbench
DeepSeek V4.1 Flash leads by +15.6
DeepSeek V4.1 Flash
83.1
GPT-5 Mini
67.5
FrontierMath-Tier-4-v2-Private
DeepSeek V4.1 Flash leads by +14.6
DeepSeek V4.1 Flash
26.8
GPT-5 Mini
12.2
FrontierMath-Tiers-1-3-v2-Private
DeepSeek V4.1 Flash leads by +21.8
DeepSeek V4.1 Flash
70.9
GPT-5 Mini
49.1
GPQA diamond
DeepSeek V4.1 Flash leads by +20.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V4.1 Flash
90.0
GPT-5 Mini
69.4
Lmca
DeepSeek V4.1 Flash leads by +15.0
DeepSeek V4.1 Flash
55.3
GPT-5 Mini
40.2
Mystery Game Puzzles
DeepSeek V4.1 Flash leads by +36.4
DeepSeek V4.1 Flash
37.2
GPT-5 Mini
0.9
OTIS Mock AIME 2024-2025
DeepSeek V4.1 Flash leads by +11.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4.1 Flash
98.3
GPT-5 Mini
86.7
Proofbench
DeepSeek V4.1 Flash leads by +45.0
DeepSeek V4.1 Flash
54.0
GPT-5 Mini
9.0
SimpleQA Verified
DeepSeek V4.1 Flash leads by +21.9
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
DeepSeek V4.1 Flash
42.9
GPT-5 Mini
21.0
Full benchmark table
| Benchmark | DeepSeek V4.1 Flash | GPT-5 Mini |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 94.5 | 54.3 |
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. | 72.9 | 4.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 45.3 | 20.0 |
Dtbench | 83.1 | 67.5 |
FrontierMath-Tier-4-v2-Private | 26.8 | 12.2 |
FrontierMath-Tiers-1-3-v2-Private | 70.9 | 49.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 90.0 | 69.4 |
Lmca | 55.3 | 40.2 |
Mystery Game Puzzles | 37.2 | 0.9 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.3 | 86.7 |
Proofbench | 54.0 | 9.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 42.9 | 21.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.05 | $0.57 | 1.0M tokens (~524 books) | $1.80 | |
| $0.25 | $2.00 | 400K tokens (~200 books) | $6.88 |