Navigate
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

DeepSeek: DeepSeek V4 Pro vs MoonshotAI: Kimi K2.7 Code

DeepSeek V4 Pro (high) leads on average score with 7.7 vs 7.5. DeepSeek V4 Pro (high) has the lower benchmark cost at $0.200 vs $0.690. DeepSeek V4 Pro (high) is faster at 79.14s vs 84.25s, with pass rates of 63.6% vs 65.2%.

Recommended modelDeepSeek V4 Pro (high)It has the best score here (7.7), while costing about 3.4x less than Kimi K2.7 Code (medium).

Last updated at: 2026-07-17

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Kimi K2.7 Code Kimi K2.7 Code medium Release: 2026-06-12
Score 7.7 7.5
Rank #44 #50
Reliability 10.0 10.0
Consistency 7.7 8.3
Tests Correct
Attempt pass rate 63.6% 65.2%
Flaky tests 6 4
Total Runs 66 66
Cost per result 2.000 6.457
Total Cost $0.200 $0.690
Input Price $0.435 / 1M $0.750 / 1M
Output Price $0.870 / 1M $3.500 / 1M
Total Input Tokens 90,748 72,073
Output Tokens 10,462 83,714
Reasoning Tokens 178,719 178,793
Response Time (avg) 79.14s 84.25s
Response Time (max) 416.76s 365.80s
Response Time (total) 1740.97s 1769.22s

Hamster playing table tennis

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

#44 DeepSeek V4 Pro

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

#50 MoonshotAI: Kimi K2.7 Code

medium
Cost
$0.025
Time
138.0s
Tokens
6,093 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
Kimi K2.7 Code 7.8 9.3 66.7% 0 146.73s 4,650 1,864 25,635

Quick Compare

Switch Comparison Pair