OpenAI o4-mini vs DeepSeek Chat V3

Performance benchmarks + pricing comparison — updated April 2026

OpenAI o4-mini

OpenAI

Updated mini reasoning model. Similar pricing to o3-mini with updated capabilities.

Input$1.10/M
Output$4.40/M
Context200K tokens
Best ForGeneral reasoning, coding tasks
Benchmark72/100

DeepSeek Chat V3

DeepSeek

Very affordable general-purpose model from DeepSeek. Strong coding and reasoning at low cost.

Input$0.270/M
Output$1.10/M
Context128K tokens
Best ForCost-sensitive projects, coding, general tasks
Benchmark62/100

Benchmark Performance Comparison

Third-party benchmark scores — higher is better. Data sourced from SWE-bench, LiveCodeBench, HumanEval, and BigCodeBench.

BenchmarkOpenAI o4-miniDeepSeek Chat V3Leader
Overall Score 72 62 o4-mini leads by 10pts
SWE-bench Verified 66 56 o4-mini leads by 10pts
LiveCodeBench 74 64 o4-mini leads by 10pts
HumanEval 92 84 o4-mini leads by 8pts
BigCodeBench 56 46 o4-mini leads by 10pts

Cost Comparison by Scenario

Estimated cost per project with 30% cache hit rate. Actual costs may vary based on usage patterns.

ScenarioOpenAI o4-miniDeepSeek Chat V3Savings
Small Script (1K lines) $0.17 $0.04 DeepSeek Chat V3 saves $0.13 (75%)
Medium Feature (10K lines) $1.27 $0.31 DeepSeek Chat V3 saves $0.95 (75%)
Large Project (50K lines) $6.33 $1.57 DeepSeek Chat V3 saves $4.75 (75%)
Code Review (5K lines) $0.30 $0.07 DeepSeek Chat V3 saves $0.23 (75%)

Value Analysis (Price per Benchmark Score Point)

Lower is better — how much you pay for each point of benchmark performance.

ModelOverall ScorePrice per Score PointVerdict
OpenAI o4-mini 72 $0.015/pt Higher cost per point
DeepSeek Chat V3 62 $0.004/pt Better value

DeepSeek Chat V3 delivers the best value at $0.004 per score point.

Strengths & Weaknesses

OpenAI o4-mini

  • + Improved reasoning at mini price
  • - New model, limited data

DeepSeek Chat V3

  • + Excellent value
  • + Strong coding focus
  • - Less general-purpose

Verdict

DeepSeek Chat V3 is cheaper at $0.270/M, but OpenAI o4-mini scores higher on benchmarks (72 vs 62).

Choose DeepSeek Chat V3 for cost-sensitive projects, OpenAI o4-mini when performance matters most.

Compare with Other Models