Can o3-mini Substitute DeepSeek-R1 for Logical Reasoning?

AI-powered reasoning fashions are taking the world by storm in 2025! With the launch of DeepSeek-R1 and o3-mini, we have now seen unprecedented ranges of logical reasoning capabilities in AI chatbots. On this article, we’ll entry these fashions through their APIs and consider their logical reasoning abilities to seek out out if o3-mini can exchange DeepSeek-R1. We will probably be evaluating their efficiency on normal benchmarks in addition to real-world functions like fixing logical puzzles and even constructing a Tetris sport! So buckle up and be a part of the journey.

DeepSeek-R1 vs o3-mini: Logical Reasoning Benchmarks

DeepSeek-R1 and o3-mini supply distinctive approaches to structured pondering and deduction, making them apt for varied sorts of complicated problem-solving duties. Earlier than we converse of their benchmark efficiency, let’s first have a sneak peek on the structure of those fashions.

o3-mini is OpenAI’s most superior reasoning mannequin. It makes use of a dense transformer structure, processing every token with all mannequin parameters for sturdy efficiency however excessive useful resource consumption. In distinction, DeepSeek’s most obvious mannequin, R1, employs a Combination-of-Specialists (MoE) framework, activating solely a subset of parameters per enter for better effectivity. This makes DeepSeek-R1 extra scalable and computationally optimized whereas sustaining stable efficiency.

Be taught Extra: Is OpenAI’s o3-mini Higher Than DeepSeek-R1?

Now what we have to see is how effectively these fashions carry out in logical reasoning duties. First, let’s take a look at their efficiency within the livebench benchmark exams.

Sources: livebench.ai

The benchmark outcomes present that OpenAI’s o3-mini outperforms DeepSeek-R1 in virtually all features, aside from math. With a world common rating of 73.94 in comparison with DeepSeek’s 71.38, the o3-mini demonstrates barely stronger total efficiency. It significantly excels in reasoning, reaching 89.58 versus DeepSeek’s 83.17, reflecting superior analytical and problem-solving capabilities.

Additionally Learn: Google Gemini 2.0 Professional vs DeepSeek-R1: Who Does Coding Higher?

DeepSeek-R1 vs o3-mini: API Pricing Comparability

Since we’re testing these fashions by means of their APIs, let’s see how a lot these fashions value.

As seen within the desk, OpenAI’s o3-mini is almost twice as costly as DeepSeek R1 by way of API prices. It costs $1.10 per million tokens for enter and $4.40 for output, whereas DeepSeek R1 gives a cheaper fee of $0.55 per million tokens for enter and $2.19 for output, making it a extra budget-friendly choice for large-scale functions.

Sources: DeepSeek-R1 | o3-mini

The best way to Entry DeepSeek-R1 and o3-mini through API

Earlier than we step into the hands-on efficiency comparability, let’s discover ways to entry DeepSeek-R1 and o3-mini utilizing APIs.

All you need to do for this, is import the mandatory libraries and api keys:

from openai import OpenAI
from IPython.show import show, Markdown
import time

with open("path_of_api_key") as file:
   openai_api_key = file.learn().strip()

with open("path_of_api_key") as file:
   deepseek_api = file.learn().strip()

DeepSeek-R1 vs o3-mini: Logical Reasoning Comparability

Now that we’ve gotten the API entry, let’s evaluate DeepSeek-R1 and o3-mini primarily based on their logical reasoning capabilities. For this, we’ll give the identical immediate to each the fashions and consider their responses primarily based on these metrics:

1. Time taken by the mannequin to generate the response,
2. High quality of the generated response, and
3. Price incurred to generate the response.

We’ll then rating the fashions 0 or 1 for every job, relying on their efficiency. So let’s check out the duties and see who emerges because the winner within the DeepSeek-R1 vs o3-mini reasoning battle!

Activity 1: Constructing a Tetris Sport

This job requires the mannequin to implement a completely purposeful Tetris sport utilizing Python, effectively managing sport logic, piece motion, collision detection, and rendering with out counting on exterior sport engines.

Immediate: “Write a python code for this drawback: generate a Python code for the Tetris sport“

Enter to DeepSeek-R1 API

INPUT_COST_CACHE_HIT = 0.14 / 1_000_000  # $0.14 per 1M tokens
INPUT_COST_CACHE_MISS = 0.55 / 1_000_000  # $0.55 per 1M tokens
OUTPUT_COST = 2.19 / 1_000_000  # $2.19 per 1M tokens

# Begin timing
task1_start_time = time.time()

# Initialize OpenAI shopper for DeepSeek API
shopper = OpenAI(api_key=api_key, base_url="https://api.deepseek.com")

messages = [
    {
        "role": "system",
        "content": """You are a professional Programmer with a large experience."""
    },
    {
        "role": "user",
        "content": """write a python code for this problem: generate a python code for Tetris game."""
    }
]

# Get token rely utilizing tiktoken (modify mannequin identify if needed)
encoding = tiktoken.get_encoding("cl100k_base")  # Use a appropriate tokenizer
input_tokens = sum(len(encoding.encode(msg["content"])) for msg in messages)

# Name DeepSeek API
response = shopper.chat.completions.create(
    mannequin="deepseek-reasoner",
    messages=messages,
    stream=False
)

# Get output token rely
output_tokens = len(encoding.encode(response.decisions[0].message.content material))

task1_end_time = time.time()

total_time_taken = task1_end_time - task1_start_time

# Assume cache miss for worst-case pricing (modify if cache information is on the market)
input_cost = (input_tokens / 1_000_000) * INPUT_COST_CACHE_MISS
output_cost = (output_tokens / 1_000_000) * OUTPUT_COST

total_cost = input_cost + output_cost

# Print outcomes
print("Response:", response.decisions[0].message.content material)
print("------------------ Complete Time Taken for Activity 1: ------------------", total_time_taken)
print(f"Enter Tokens: {input_tokens}, Output Tokens: {output_tokens}")
print(f"Estimated Price: ${total_cost:.6f}")

# Show outcome
from IPython.show import Markdown
show(Markdown(response.decisions[0].message.content material))

Response by DeepSeek-R1

You will discover DeepSeek-R1’s full response right here.

Output token value:

Enter Tokens: 28 | Output Tokens: 3323 | Estimated Price: $0.0073

Code Output

Enter to o3-mini API

task1_start_time = time.time()


shopper = OpenAI(api_key=api_key)

messages = messages=[
       {
       "role": "system",
       "content": """You are a professional Programmer with a large experience ."""


   },
{
       "role": "user",
       "content": """write a python code for this problem: generate a python code for Tetris game.
"""


   }
   ]


# Use a appropriate encoding (cl100k_base is the best choice for brand spanking new OpenAI fashions)
encoding = tiktoken.get_encoding("cl100k_base")


# Calculate token counts
input_tokens = sum(len(encoding.encode(msg["content"])) for msg in messages)


completion = shopper.chat.completions.create(
   mannequin="o3-mini-2025-01-31",
   messages=messages
)


output_tokens = len(encoding.encode(completion.decisions[0].message.content material))


task1_end_time = time.time()




input_cost_per_1k = 0.0011  # Instance: $0.005 per 1,000 enter tokens
output_cost_per_1k = 0.0044  # Instance: $0.015 per 1,000 output tokens


# Calculate value
input_cost = (input_tokens / 1000) * input_cost_per_1k
output_cost = (output_tokens / 1000) * output_cost_per_1k
total_cost = input_cost + output_cost
print(completion.decisions[0].message)
print("----------------=Complete Time Taken for job 1:----------------- ", task1_end_time - task1_start_time)
print(f"Enter Tokens: {input_tokens}, Output Tokens: {output_tokens}")
print(f"Estimated Price: ${total_cost:.6f}")


# Show outcome
from IPython.show import Markdown
show(Markdown(completion.decisions[0].message.content material))

Response by o3-mini

You will discover o3-mini’s full response right here.

Output token value: 

Enter Tokens: 28 | Output Tokens: 3235 | Estimated Price: $0.014265

Code Output

Comparative Evaluation

On this job, the fashions have been required to generate purposeful Tetris code that enables for precise gameplay. DeepSeek-R1 efficiently produced a completely working implementation, as demonstrated within the code output video. In distinction, whereas o3-mini’s code appeared well-structured, it encountered errors throughout execution. Because of this, DeepSeek-R1 outperforms o3-mini on this situation, delivering a extra dependable and playable resolution.

Rating: DeepSeek-R1: 1 | o3-mini: 0

Activity 2: Analyzing Relational Inequalities

This job requires the mannequin to effectively analyze relational inequalities quite than counting on primary sorting strategies.

Immediate: “ Within the following query assuming the given statements to be true, discover which of the conclusion among the many given conclusions is/are positively true after which give your solutions accordingly. 

Statements: 

H > F ≤ O ≤ L; F ≥ V

Conclusions: I. L ≥ V II. O > D 

The choices are:

 A. Solely I is true 

B. Solely II is true 

C. Each I and II are true

D. Both I or II is true 

E. Neither I nor II is true.”

Enter to DeepSeek-R1 API

INPUT_COST_CACHE_HIT = 0.14 / 1_000_000  # $0.14 per 1M tokens
INPUT_COST_CACHE_MISS = 0.55 / 1_000_000  # $0.55 per 1M tokens
OUTPUT_COST = 2.19 / 1_000_000  # $2.19 per 1M tokens

# Begin timing
task2_start_time = time.time()

# Initialize OpenAI shopper for DeepSeek API
shopper = OpenAI(api_key=api_key, base_url="https://api.deepseek.com")

messages = [
    {"role": "system", "content": "You are an expert in solving Reasoning Problems. Please solve the given problem."},
    {"role": "user", "content": """ In the following question, assuming the given statements to be true, find which of the conclusions among given conclusions is/are definitely true and then give your answers accordingly.
        Statements: H > F ≤ O ≤ L; F ≥ V  D
        The options are:
        A. Only I is true 
        B. Only II is true
        C. Both I and II are true
        D. Either I or II is true
        E. Neither I nor II is true
    """}
]

# Get token rely utilizing tiktoken (modify mannequin identify if needed)
encoding = tiktoken.get_encoding("cl100k_base")  # Use a appropriate tokenizer
input_tokens = sum(len(encoding.encode(msg["content"])) for msg in messages)

# Name DeepSeek API
response = shopper.chat.completions.create(
    mannequin="deepseek-reasoner",
    messages=messages,
    stream=False
)

# Get output token rely
output_tokens = len(encoding.encode(response.decisions[0].message.content material))

task2_end_time = time.time()

total_time_taken = task2_end_time - task2_start_time

# Assume cache miss for worst-case pricing (modify if cache information is on the market)
input_cost = (input_tokens / 1_000_000) * INPUT_COST_CACHE_MISS
output_cost = (output_tokens / 1_000_000) * OUTPUT_COST

total_cost = input_cost + output_cost

# Print outcomes
print("Response:", response.decisions[0].message.content material)
print("------------------ Complete Time Taken for Activity 2: ------------------", total_time_taken)
print(f"Enter Tokens: {input_tokens}, Output Tokens: {output_tokens}")
print(f"Estimated Price: ${total_cost:.6f}")

# Show outcome
from IPython.show import Markdown
show(Markdown(response.decisions[0].message.content material))

Output token value:

Enter Tokens: 136 | Output Tokens: 352 | Estimated Price: $0.000004

Response by DeepSeek-R1

Enter to o3-mini API

task2_start_time = time.time()

shopper = OpenAI(api_key=api_key)

messages = [
    {
        "role": "system",
        "content": """You are an expert in solving Reasoning Problems. Please solve the given problem"""
    },
    {
        "role": "user",
        "content": """In the following question, assuming the given statements to be true, find which of the conclusions among given conclusions is/are definitely true and then give your answers accordingly.
        Statements: H > F ≤ O ≤ L; F ≥ V  D
        The options are:
        A. Only I is true 
        B. Only II is true
        C. Both I and II are true
        D. Either I or II is true
        E. Neither I nor II is true
        """
    }
]

# Use a appropriate encoding (cl100k_base is the best choice for brand spanking new OpenAI fashions)
encoding = tiktoken.get_encoding("cl100k_base")

# Calculate token counts
input_tokens = sum(len(encoding.encode(msg["content"])) for msg in messages)

completion = shopper.chat.completions.create(
    mannequin="o3-mini-2025-01-31",
    messages=messages
)

output_tokens = len(encoding.encode(completion.decisions[0].message.content material))

task2_end_time = time.time()


input_cost_per_1k = 0.0011  # Instance: $0.005 per 1,000 enter tokens
output_cost_per_1k = 0.0044  # Instance: $0.015 per 1,000 output tokens

# Calculate value
input_cost = (input_tokens / 1000) * input_cost_per_1k
output_cost = (output_tokens / 1000) * output_cost_per_1k
total_cost = input_cost + output_cost


# Print outcomes
print(completion.decisions[0].message)
print("----------------=Complete Time Taken for job 2:----------------- ", task2_end_time - task2_start_time)
print(f"Enter Tokens: {input_tokens}, Output Tokens: {output_tokens}")
print(f"Estimated Price: ${total_cost:.6f}")

# Show outcome
from IPython.show import Markdown
show(Markdown(completion.decisions[0].message.content material))

Output token value:

Enter Tokens: 135 | Output Tokens: 423 | Estimated Price: $0.002010

Response by o3-mini

Comparative Evaluation

o3-mini delivers essentially the most environment friendly resolution, offering a concise but correct response in considerably much less time. It maintains readability whereas making certain logical soundness, making it best for fast reasoning duties. DeepSeek-R1, whereas equally appropriate, is way slower and extra verbose. Its detailed breakdown of logical relationships enhances explainability however could really feel extreme for simple evaluations. Although each fashions arrive on the similar conclusion, o3-mini’s pace and direct method make it the higher selection for sensible use.

Rating: DeepSeek-R1: 0 | o3-mini: 1

Activity 3: Logical Reasoning in Math

This job challenges the mannequin to acknowledge numerical patterns, which can contain arithmetic operations, multiplication, or a mixture of mathematical guidelines. As an alternative of brute-force looking, the mannequin should undertake a structured method to infer the hidden logic effectively.

Immediate: “Research the given matrix fastidiously and choose the quantity from among the many given choices that may exchange the query mark (?) in it.

____________

|  7  | 13  | 174|

|  9  | 25  | 104|

|  11  | 30   | ?   |

|_____|____|___|

The choices are:

 A 335

B 129

C 431

D 100

 Please point out your method that you’ve taken at every step.“

Enter to DeepSeek-R1 API

INPUT_COST_CACHE_HIT = 0.14 / 1_000_000  # $0.14 per 1M tokens
INPUT_COST_CACHE_MISS = 0.55 / 1_000_000  # $0.55 per 1M tokens
OUTPUT_COST = 2.19 / 1_000_000  # $2.19 per 1M tokens

# Begin timing
task3_start_time = time.time()

# Initialize OpenAI shopper for DeepSeek API
shopper = OpenAI(api_key=api_key, base_url="https://api.deepseek.com")

messages = [
{
		"role": "system",
		"content": """You are a Expert in solving Reasoning Problems. Please solve the given problem"""

	},
  
	
]
# Get token rely utilizing tiktoken (modify mannequin identify if needed)
encoding = tiktoken.get_encoding("cl100k_base")  # Use a appropriate tokenizer
input_tokens = sum(len(encoding.encode(msg["content"])) for msg in messages)

# Name DeepSeek API
response = shopper.chat.completions.create(
    mannequin="deepseek-reasoner",
    messages=messages,
    stream=False
)

# Get output token rely
output_tokens = len(encoding.encode(response.decisions[0].message.content material))

task3_end_time = time.time()

total_time_taken = task3_end_time - task3_start_time

# Assume cache miss for worst-case pricing (modify if cache information is on the market)
input_cost = (input_tokens / 1_000_000) * INPUT_COST_CACHE_MISS
output_cost = (output_tokens / 1_000_000) * OUTPUT_COST

total_cost = input_cost + output_cost

# Print outcomes
print("Response:", response.decisions[0].message.content material)
print("------------------ Complete Time Taken for Activity 3: ------------------", total_time_taken)
print(f"Enter Tokens: {input_tokens}, Output Tokens: {output_tokens}")
print(f"Estimated Price: ${total_cost:.6f}")

# Show outcome
from IPython.show import Markdown
show(Markdown(response.decisions[0].message.content material))

Output token value:

Enter Tokens: 134 | Output Tokens: 274 | Estimated Price: $0.000003

Response by DeepSeek-R1

Enter to o3-mini API

task3_start_time = time.time()
shopper = OpenAI(api_key=api_key)
messages = [
        {
		"role": "system",
		"content": """You are a Expert in solving Reasoning Problems. Please solve the given problem"""

	},
  
	
    ]

# Use a appropriate encoding (cl100k_base is the best choice for brand spanking new OpenAI fashions)
encoding = tiktoken.get_encoding("cl100k_base")

# Calculate token counts
input_tokens = sum(len(encoding.encode(msg["content"])) for msg in messages)

completion = shopper.chat.completions.create(
    mannequin="o3-mini-2025-01-31",
    messages=messages
)

output_tokens = len(encoding.encode(completion.decisions[0].message.content material))

task3_end_time = time.time()


input_cost_per_1k = 0.0011  # Instance: $0.005 per 1,000 enter tokens
output_cost_per_1k = 0.0044  # Instance: $0.015 per 1,000 output tokens

# Calculate value
input_cost = (input_tokens / 1000) * input_cost_per_1k
output_cost = (output_tokens / 1000) * output_cost_per_1k
total_cost = input_cost + output_cost

# Print outcomes
print(completion.decisions[0].message)
print("----------------=Complete Time Taken for job 3:----------------- ", task3_end_time - task3_start_time)
print(f"Enter Tokens: {input_tokens}, Output Tokens: {output_tokens}")
print(f"Estimated Price: ${total_cost:.6f}")

# Show outcome
from IPython.show import Markdown
show(Markdown(completion.decisions[0].message.content material))

Output token value:

Enter Tokens: 134 | Output Tokens: 736 | Estimated Price: $0.003386

Output by o3-mini

Comparative Evaluation

Right here, the sample adopted in every row is:

(1st quantity)^3−(2nd quantity)^2 = third quantity

Making use of this sample:

• Row 1: 7^3 – 13^2 = 343 – 169 = 174
• Row 2: 9^3 – 25^2 = 729 – 625 = 104
• Row 3: 11^3 – 30^2 = 1331 – 900 = 431

Therefore, the right reply is 431.

DeepSeek-R1 appropriately identifies and applies this sample, resulting in the proper reply. Its structured method ensures accuracy, although it takes considerably longer to compute the outcome. o3-mini, alternatively, fails to ascertain a constant sample. It makes an attempt a number of operations, resembling multiplication, addition, and exponentiation, however doesn’t arrive at a definitive reply. This ends in an unclear and incorrect response. General, DeepSeek-R1 outperforms o3-mini in logical reasoning and accuracy, whereas O3-mini struggles attributable to its inconsistent and ineffective method.

Rating: DeepSeek-R1: 1 | o3-mini: 0

Ultimate Rating: DeepSeek-R1: 2 | o3-mini: 1

Logical Reasoning Comparability Abstract

Conclusion

As we have now seen on this comparability, each DeepSeek-R1 and o3-mini display distinctive strengths catering to completely different wants. DeepSeek-R1 excels in accuracy-driven duties, significantly in mathematical reasoning and sophisticated code technology, making it a powerful candidate for functions requiring logical depth and correctness. Nevertheless, one vital downside is its slower response instances, partly attributable to ongoing server upkeep points which have affected its accessibility. Alternatively, o3-mini gives considerably sooner response instances, however its tendency to supply incorrect outcomes limits its reliability for high-stakes reasoning duties.

This evaluation underscores the trade-offs between pace and accuracy in language fashions. Whereas o3-mini could also be helpful for fast, low-risk functions, DeepSeek-R1 stands out because the superior selection for reasoning-intensive duties, supplied its latency points are addressed. As AI fashions proceed to evolve, hanging a stability between efficiency effectivity and correctness will probably be key to optimizing AI-driven workflows throughout varied domains.

Additionally Learn: Can OpenAI’s o3-mini Beat Claude Sonnet 3.5 in Coding?

Regularly Requested Questions

Hiya! I am Vipin, a passionate information science and machine studying fanatic with a powerful basis in information evaluation, machine studying algorithms, and programming. I’ve hands-on expertise in constructing fashions, managing messy information, and fixing real-world issues. My purpose is to use data-driven insights to create sensible options that drive outcomes. I am desirous to contribute my abilities in a collaborative setting whereas persevering with to be taught and develop within the fields of Information Science, Machine Studying, and NLP.