Navigate
AI BENCHY
Advertise here

Claude Opus 4.8 vs DeepSeek V4 Flash 0731 (medium)

The average score is effectively tied at 7.3 vs 7.3. DeepSeek V4 Flash 0731 (medium) has the lower benchmark cost at $0.106 vs $1.166. Claude Opus 4.8 is faster at 4.91s vs 85.80s, with pass rates of 63.6% vs 72.7%.

Last updated at: 2026-08-01

Rank
#79
Total Output Tokens
16,797
Response Time (avg)
4.91s
Total Cost
$1.166
Rank
#76
Total Output Tokens
618,417
Response Time (avg)
85.80s
Total Cost
$0.106
Recommended model DeepSeek V4 Flash 0731 (medium)

It has the best score here (7.3), while costing about 11.1x less than Claude Opus 4.8.

Detailed comparison

Metric Claude Opus 4.8 Claude Opus 4.8 none Release: 2026-05-28 DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 medium Release: 2026-08-01
Score 7.3 7.3
Rank #79 #76
Reliability 10.0 9.8
Consistency 9.2 7.1
Tests Correct
Attempt pass rate 63.6% 72.7%
Flaky tests 2 8
Total Runs 66 66
Cost per result 8.969 0.956
Total Cost $1.166 $0.106
Input Price $5.000 / 1M $0.140 / 1M
Output Price $25.000 / 1M $0.280 / 1M
Total Input Tokens 149,206 89,768
Output Tokens 16,797 66,624
Reasoning Tokens 0 551,793
Response Time (avg) 4.91s 85.80s
Response Time (max) 35.03s 288.78s
Response Time (total) 108.03s 1887.69s

Model generation showcase

Hamster playing table tennis

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

#79 Claude Opus 4.8

none
Cost
$0.053
Time
22.0s
Tokens
2,253 tok

#76 DeepSeek V4 Flash 0731

medium
Cost
$0.004
Time
93.3s
Tokens
13,252 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
Claude Opus 4.8 5.5 10.0 33.3% 0 3.29s 10,590 1,332 0
DeepSeek V4 Flash 0731 6.4 4.4 77.8% 2 198.78s 6,032 4,109 160,154

Quick Compare

Switch Comparison Pair