Navigate
AI BENCHY
Advertise here

DeepSeek: DeepSeek V4 Pro vs Thinking Machines: Inkling

Inkling (medium) leads on average score with 8.0 vs 7.7. DeepSeek V4 Pro (high) has the lower benchmark cost at $0.200 vs $0.391. Inkling (medium) is faster at 16.21s vs 79.14s, with pass rates of 63.6% vs 78.8%.

Recommended modelInkling (medium)It has the best score here (8.0), while responding about 4.9x faster than DeepSeek V4 Pro (high).

Last updated at: 2026-07-18

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Inkling Inkling medium Release: 2026-07-18
Score 7.7 8.0
Rank #46 #32
Reliability 10.0 9.8
Consistency 7.7 8.2
Tests Correct
Attempt pass rate 63.6% 78.8%
Flaky tests 6 5
Total Runs 66 66
Cost per result 2.000 2.604
Total Cost $0.200 $0.391
Input Price $0.435 / 1M $1.000 / 1M
Output Price $0.870 / 1M $4.050 / 1M
Total Input Tokens 90,748 124,053
Output Tokens 10,462 12,189
Reasoning Tokens 178,719 53,597
Response Time (avg) 79.14s 16.21s
Response Time (max) 416.76s 85.12s
Response Time (total) 1740.97s 356.54s

Hamster playing table tennis

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

#46 DeepSeek V4 Pro

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

#32 Thinking Machines: Inkling

medium
Cost
$0.004
Time
11.2s
Tokens
852 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
DeepSeek V4 Pro 6.3 8.7 33.3% 0 243.00s 5,090 383 84,580
Inkling 8.4 7.8 77.8% 1 25.20s 7,374 525 14,457

Quick Compare

Switch Comparison Pair