Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs xAI: Grok 4.20

Summary

DeepSeek V4 Pro vs Grok 4.20 benchmark comparison: Grok 4.20 leads on average score with 7.3 vs 7.2. DeepSeek V4 Pro has the lower benchmark cost at $0.030 vs $0.609. DeepSeek V4 Pro is faster at 5.30s vs 27.68s, with pass rates of 52.4% vs 63.5%.

Recommended model: DeepSeek V4 Pro - Its score stays close to the best score here (7.2 vs 7.3), while costing about 20.8x less than Grok 4.20.

Last updated at: 2026-06-12

Metric DeepSeek V4 Pro DeepSeek V4 Pro none Release: 2026-04-24 Grok 4.20 Grok 4.20 medium Release: 2026-03-31
Score 7.2 7.3
Rank #61 #55
Reliability 9.9 10.0
Consistency 8.8 8.8
Tests Correct
Attempt pass rate 52.4% 63.5%
Flaky tests 3 3
Total Runs 61 63
Cost per result 0.293 8.309
Total Cost $0.030 $0.609
Input Price $0.435 / 1M $1.250 / 1M
Output Price $0.870 / 1M $2.500 / 1M
Total Input Tokens 53,078 44,433
Output Tokens 7,047 1,819
Reasoning Tokens 0 219,524
Response Time (avg) 5.30s 27.68s
Response Time (max) 23.74s 199.66s
Response Time (total) 111.39s 581.26s

Generation showcase

Hamster playing table tennis

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

#61 DeepSeek V4 Pro

none
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

#55 xAI: Grok 4.20

medium
Cost
$0.041
Time
110.3s
Tokens
16,336 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 3.2 6.1 16.7% 2 4.02s 540 1,168 0
Grok 4.20 8.2 7.9 83.3% 1 3.95s 2,010 287 8,312
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.6 10.0 33.3% 0 5.62s 6,795 1,123 0
Grok 4.20 6.3 6.6 55.6% 1 109.93s 8,307 268 103,150
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 9.5 10.0 100.0% 0 23.74s 27,529 2,235 0
Grok 4.20 10.0 10.0 100.0% 0 17.40s 12,909 232 9,556
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 10.0 10.0 100.0% 0 4.61s 7,568 200 0
Grok 4.20 10.0 10.0 100.0% 0 4.17s 7,761 180 5,333
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.3 10.0 33.3% 0 3.72s 666 24 0
Grok 4.20 5.3 10.0 33.3% 0 27.03s 1,764 375 49,339
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.0 10.0 0.0% 0 2.05s 471 126 0
Grok 4.20 3.9 2.6 33.3% 1 24.48s 825 65 6,440
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.3 5.8 66.7% 1 4.12s 627 713 0
Grok 4.20 9.8 10.0 100.0% 0 4.26s 1,362 57 6,419
Puzzle Solving 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 3.61s 594 442 0
Grok 4.20 7.7 10.0 66.7% 0 6.22s 1,689 149 7,913
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 7.40s 8,105 328 0
Grok 4.20 3.0 10.0 0.0% 0 13.68s 7,275 197 6,620
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 5.76s 183 688 0
Grok 4.20 3.0 10.0 0.0% 0 63.48s 531 9 16,442

Quick Compare

Switch Comparison Pair