Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs OpenAI: GPT-5.4 Nano

Summary

DeepSeek V4 Pro vs GPT-5.4 Nano benchmark comparison: DeepSeek V4 Pro leads on average score with 6.3 vs 4.8. GPT-5.4 Nano has the lower benchmark cost at $0.011 vs $0.079. GPT-5.4 Nano is faster at 1.48s vs 65.21s, with pass rates of 52.4% vs 30.2%.

Recommended model: GPT-5.4 Nano - It offers the best overall trade-off: a competitive score (4.8), lower cost than DeepSeek V4 Pro, and balanced response time.

Last updated at: 2026-06-12

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 GPT-5.4 Nano GPT-5.4 Nano none Release: 2026-03-17
Score 6.3 4.8
Rank #90 #149
Reliability 9.0 10.0
Consistency 7.6 8.2
Tests Correct
Attempt pass rate 52.4% 30.2%
Flaky tests 6 5
Total Runs 63 63
Cost per result 2.869 0.259
Total Cost $0.079 $0.011
Input Price $0.435 / 1M $0.200 / 1M
Output Price $0.870 / 1M $1.250 / 1M
Total Input Tokens 32,240 34,212
Output Tokens 12,250 2,784
Reasoning Tokens 72,257 0
Response Time (avg) 65.21s 1.48s
Response Time (max) 358.35s 4.47s
Response Time (total) 1304.19s 31.01s

Generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#90 DeepSeek V4 Pro

high
Cost
$0.023
Time
257.6s
Tokens
14,870 tok

#149 GPT-5.4 Nano

none
Cost
$0.008
Time
46.1s
Tokens
5,735 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.4 7.9 58.3% 1 16.53s 448 71 3,617
GPT-5.4 Nano 3.5 8.0 16.7% 1 1.18s 606 800 0
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.3 6.4 11.1% 1 118.23s 1,966 111 20,940
GPT-5.4 Nano 4.6 7.9 22.2% 1 2.22s 7,305 613 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 65.02s 14,016 465 5,914
GPT-5.4 Nano 3.0 10.0 0.0% 0 3.84s 11,019 280 0
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 7.3 5.9 83.3% 1 23.62s 5,633 229 1,710
GPT-5.4 Nano 6.5 10.0 50.0% 0 1.11s 7,140 219 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 2.9 7.2 11.1% 1 205.66s 430 10,529 28,089
GPT-5.4 Nano 2.9 4.4 22.2% 2 926ms 723 52 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.1 3.1 66.7% 1 25.09s 314 76 1,152
GPT-5.4 Nano 3.8 2.5 33.3% 1 1.31s 477 180 0
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 41.16s 627 205 2,416
GPT-5.4 Nano 6.3 10.0 50.0% 0 784ms 660 89 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.9 7.2 55.6% 1 34.84s 544 139 4,019
GPT-5.4 Nano 5.4 10.0 33.3% 0 1.25s 642 308 0
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 21.33s 8,079 372 593
GPT-5.4 Nano 10.0 10.0 100.0% 0 3.40s 5,445 222 0
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.0 10.0 0.0% 0 39.14s 183 53 3,807
GPT-5.4 Nano 3.0 10.0 0.0% 0 773ms 195 21 0

Quick Compare

Switch Comparison Pair