Navigate
AI BENCHY
Your ad here

AI BENCHY Compare

Anthropic: Claude Sonnet 4.6 vs DeepSeek: DeepSeek V4 Pro

Last updated at: 2026-04-24

Metric Claude Sonnet 4.6 Claude Sonnet 4.6 none Release: 2026-02-17 DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24
Score 7.4 7.4
Rank #48 #50
Consistency 9.6 10.0
Tests Correct
Attempt pass rate 64.8% 61.1%
Flaky tests 1 0
Total Runs 54 24
Cost per result 2.376 1.385
Total Cost $0.262 $0.153
Input Price $3.000 / 1M $1.740 / 1M
Output Price $15.000 / 1M $3.480 / 1M
Output Tokens 7,433 584
Reasoning Tokens 0 37,708
Response Time (avg) 4.98s 78.45s
Response Time (max) 23.84s 351.99s
Response Time (total) 54.83s 1255.22s

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) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 4.8 10.0 25.0% 0 2.94s 1,214 0
DeepSeek V4 Pro 8.3 10.0 75.0% 0 32.12s 64 1,799
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 3.67s 523 0
DeepSeek V4 Pro 10.0 10.0 100.0% 0 93.00s 82 2,808
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 9.5 10.0 100.0% 0 23.84s 3,766 0
DeepSeek V4 Pro 10.0 10.0 100.0% 0 71.08s 134 2,163
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 3.43s 252 0
DeepSeek V4 Pro 10.0 10.0 100.0% 0 63.00s 67 1,071
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 7.7 10.0 66.7% 0 3.54s 413 0
DeepSeek V4 Pro 5.3 10.0 33.3% 0 202.56s 11 25,343
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 6.1 3.1 66.7% 1 2.56s 192 0
DeepSeek V4 Pro 5.0 10.0 0.0% 0 26.96s 51 734
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 6.5 10.0 50.0% 0 1.96s 90 0
DeepSeek V4 Pro 3.0 10.0 0.0% 0 0ms 0 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 7.7 10.0 66.7% 0 2.92s 536 0
DeepSeek V4 Pro 7.7 10.0 66.7% 0 63.66s 91 3,617
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 4.11s 447 0
DeepSeek V4 Pro 10.0 10.0 100.0% 0 11.05s 84 173

Quick Compare

Switch Comparison Pair