Navigate
AI BENCHY
Advertise here

Seed-2.0-Code (high) vs DeepSeek V4 Pro

The average score is effectively tied at 6.9 vs 6.9. DeepSeek V4 Pro has the lower benchmark cost at $0.256 vs $1.312. DeepSeek V4 Pro is faster at 11.55s vs 127.79s, with pass rates of 71.2% vs 51.5%.

Last updated at: 2026-08-12

Rank
#123
Total Output Tokens
423,424
Response Time (avg)
127.79s
Total Cost
$1.312
Rank
#119
Total Output Tokens
35,551
Response Time (avg)
11.55s
Total Cost
$0.256
Recommended model DeepSeek V4 Pro

It has the best score here (6.9), while costing about 5.1x less than Seed-2.0-Code (high).

Detailed comparison

Metric Seed-2.0-Code Seed-2.0-Code high Release: 2026-08-12 DeepSeek V4 Pro DeepSeek V4 Pro none Release: 2026-04-24
Score 6.9 6.9
Rank #123 #119
Reliability 6.0 10.0
Consistency 7.0 8.6
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 71.2% 51.5%
Flaky tests 8 4
Total Runs 66 66
Cost per result 11.921 0.954
Total Cost $1.312 $0.256
Input Price $0.500 / 1M $1.169 / 1M
Output Price $3.000 / 1M $2.337 / 1M
Total Input Tokens 81,961 148,069
Output Tokens 7,187 35,551
Reasoning Tokens 416,237 0
Response Time (avg) 127.79s 11.55s
Response Time (max) 675.30s 119.44s
Response Time (total) 2811.27s 254.11s
Parameters ~200B total (~20B active) 1.6T total (49B active)
Availability Closed Open source

Model generation showcase

Hamster playing table tennis

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

#123 Seed-2.0-Code

high
Cost
$0.037
Time
183.6s
Tokens
12,388 tok

#119 DeepSeek V4 Pro

none
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 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

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Seed-2.0-Code 5.9 4.4 66.7% 2 266.74s 6,750 432 124,956
DeepSeek V4 Pro 5.6 10.0 33.3% 0 13.38s 7,275 5,500 0

Quick Compare

Switch Comparison Pair