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: DeepSeek V4 Pro leads on average score with 6.0 vs 5.4. Grok 4.20 has the lower benchmark cost at $0.057 vs $0.079. Grok 4.20 is faster at 1.11s vs 65.21s, with pass rates of 52.4% vs 33.3%.

Recommended model: Grok 4.20 - Its score stays close to the best score here (5.4 vs 6.0), while responding about 58.8x faster than DeepSeek V4 Pro.

Last updated at: 2026-06-10

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Grok 4.20 Grok 4.20 none Release: 2026-03-31
Score 6.0 5.4
Rank #104 #128
Reliability 9.0 N/A
Consistency 7.6 10.0
Tests Correct
Attempt pass rate 52.4% 33.3%
Flaky tests 6 0
Total Runs 63 54
Cost per result 2.869 1.570
Total Cost $0.079 $0.057
Input Price $0.435 / 1M $1.250 / 1M
Output Price $0.870 / 1M $2.500 / 1M
Total Input Tokens 32,240 41,313
Output Tokens 12,250 1,923
Reasoning Tokens 72,257 0
Response Time (avg) 65.21s 1.11s
Response Time (max) 358.35s 6.04s
Response Time (total) 1304.19s 19.96s

Generation showcase

Hamster playing table tennis

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

#104 DeepSeek V4 Pro

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

#128 xAI: Grok 4.20

none
Cost
$0.004
Time
6.5s
Tokens
1,367 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
Grok 4.20 4.8 10.0 25.0% 0 501ms 1,986 267 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
Grok 4.20 3.4 9.3 0.0% 0 1.22s 1,074 312 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
Grok 4.20 3.0 10.0 0.0% 0 6.04s 17,673 282 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
Grok 4.20 10.0 10.0 100.0% 0 522ms 7,749 207 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
Grok 4.20 3.0 10.0 0.0% 0 687ms 1,746 325 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
Grok 4.20 4.8 10.0 0.0% 0 659ms 819 83 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
Grok 4.20 6.3 10.0 50.0% 0 445ms 1,350 60 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
Grok 4.20 5.3 10.0 33.3% 0 473ms 1,671 198 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
Grok 4.20 10.0 10.0 100.0% 0 4.63s 7,245 189 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
Grok 4.20 - - - - - - - - -

Quick Compare

Switch Comparison Pair