Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

Anthropic: Claude Opus 4.8 vs DeepSeek: DeepSeek V4 Pro

Summary

Claude Opus 4.8 vs DeepSeek V4 Pro benchmark comparison: Claude Opus 4.8 leads on average score with 7.7 vs 7.6. DeepSeek V4 Pro has the lower benchmark cost at $0.157 vs $1.270. Claude Opus 4.8 is faster at 10.83s vs 77.20s, with pass rates of 79.4% vs 66.7%.

Recommended model: Claude Opus 4.8 - It has the best score here (7.7), while responding about 7.1x faster than DeepSeek V4 Pro.

Last updated at: 2026-06-30

Metric Claude Opus 4.8 Claude Opus 4.8 low Release: 2026-05-28 DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24
Score 7.7 7.6
Rank #38 #43
Reliability 10.0 9.3
Consistency 8.8 7.0
Tests Correct
Attempt pass rate 79.4% 66.7%
Flaky tests 3 8
Total Runs 63 63
Cost per result 8.466 1.742
Total Cost $1.270 $0.157
Input Price $5.000 / 1M $0.435 / 1M
Output Price $25.000 / 1M $0.870 / 1M
Total Input Tokens 60,946 38,726
Output Tokens 31,771 6,334
Reasoning Tokens 6,831 159,151
Response Time (avg) 10.83s 77.20s
Response Time (max) 127.97s 416.76s
Response Time (total) 227.39s 1621.17s

Generation showcase

Hamster playing table tennis

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

#38 Claude Opus 4.8

low
Cost
$0.031
Time
14.1s
Tokens
1,345 tok

#43 DeepSeek V4 Pro

high
Cost
$0.023
Time
257.6s
Tokens
14,870 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
Claude Opus 4.8 10.0 10.0 100.0% 0 3.30s 834 793 371
DeepSeek V4 Pro 5.7 5.9 58.3% 2 25.70s 536 149 3,214
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 6.6 4.6 77.8% 2 7.58s 10,590 3,637 809
DeepSeek V4 Pro 6.1 4.6 66.7% 2 243.00s 5,090 383 84,580
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 9.8 10.0 100.0% 0 20.84s 23,500 2,216 1,081
DeepSeek V4 Pro 10.0 10.0 100.0% 0 38.17s 14,060 454 5,836
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 6.3 5.8 66.7% 1 2.27s 10,503 310 0
DeepSeek V4 Pro 10.0 10.0 100.0% 0 25.03s 7,690 274 2,166
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 5.3 10.0 33.3% 0 45.53s 975 23,311 3,908
DeepSeek V4 Pro 3.6 7.2 22.2% 1 151.46s 569 4,404 50,391
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 10.0 10.0 100.0% 0 2.55s 708 231 0
DeepSeek V4 Pro 10.0 10.0 100.0% 0 8.83s 471 115 1,013
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 9.8 10.0 100.0% 0 2.78s 909 111 221
DeepSeek V4 Pro 7.8 6.6 83.3% 1 8.73s 627 66 2,726
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 10.0 10.0 100.0% 0 3.01s 894 592 184
DeepSeek V4 Pro 6.9 4.9 77.8% 2 56.85s 591 178 2,563
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 10.0 10.0 100.0% 0 6.85s 11,775 370 35
DeepSeek V4 Pro 9.8 10.0 100.0% 0 15.92s 8,909 295 701
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 3.0 10.0 0.0% 0 5.48s 258 200 222
DeepSeek V4 Pro 3.0 10.0 0.0% 0 34.01s 183 16 5,961

Quick Compare

Switch Comparison Pair