Navigate
AI BENCHY
Advertise here

DeepSeek V4 Pro (high) vs MiniMax M3 (medium)

The average score is effectively tied at 7.7 vs 7.6. DeepSeek V4 Pro (high) has the lower benchmark cost at $0.200 vs $0.286. MiniMax M3 (medium) is faster at 74.98s vs 79.14s, with pass rates of 63.6% vs 66.7%.

Last updated at: 2026-08-01

Rank
#58
Total Output Tokens
189,181
Response Time (avg)
79.14s
Total Cost
$0.200
Rank
#59
Total Output Tokens
251,469
Response Time (avg)
74.98s
Total Cost
$0.286
Recommended model DeepSeek V4 Pro (high)

It has the strongest score in this comparison (7.7) and the best overall balance of cost and response time across all 2 models.

Detailed comparison

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 MiniMax M3 MiniMax M3 medium Release: 2026-06-01
Score 7.7 7.6
Rank #58 #59
Reliability 10.0 9.7
Consistency 7.7 8.0
Tests Correct
Attempt pass rate 63.6% 66.7%
Flaky tests 6 5
Total Runs 66 66
Cost per result 2.000 2.376
Total Cost $0.200 $0.286
Input Price $0.435 / 1M $0.300 / 1M
Output Price $0.870 / 1M $1.200 / 1M
Total Input Tokens 90,748 121,990
Output Tokens 10,462 77,916
Reasoning Tokens 178,719 173,553
Response Time (avg) 79.14s 74.98s
Response Time (max) 416.76s 431.03s
Response Time (total) 1740.97s 1574.56s

Model generation showcase

Hamster playing table tennis

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

#58 DeepSeek V4 Pro

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

#59 MiniMax M3

medium
Cost
$0.012
Time
154.4s
Tokens
10,018 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
MiniMax M3 6.1 6.5 55.6% 1 144.74s 5,804 6,223 32,667

Quick Compare

Switch Comparison Pair