Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V3.2 vs Mistral: Mistral Small 4

Summary

DeepSeek V3.2 vs Mistral Small 4 (medium) benchmark comparison: DeepSeek V3.2 leads on average score with 5.3 vs 5.1. DeepSeek V3.2 has the lower benchmark cost at $0.017 vs $0.068. Mistral Small 4 (medium) is faster at 9.40s vs 13.83s, with pass rates of 39.7% vs 44.4%.

Recommended model: DeepSeek V3.2 - It has the best score here (5.3), while costing about 4.0x less than Mistral Small 4 (medium).

Last updated at: 2026-07-09

Metric DeepSeek V3.2 DeepSeek V3.2 none Release: 2025-12-01 Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16
Score 5.3 5.1
Rank #145 #152
Reliability 10.0 10.0
Consistency 7.6 6.9
Tests Correct
Attempt pass rate 39.7% 44.4%
Flaky tests 6 8
Total Runs 63 63
Cost per result 0.306 1.344
Total Cost $0.017 $0.068
Input Price $0.229 / 1M $0.150 / 1M
Output Price $0.344 / 1M $0.600 / 1M
Total Input Tokens 55,997 42,576
Output Tokens 11,165 24,184
Reasoning Tokens 0 84,678
Response Time (avg) 13.83s 9.40s
Response Time (max) 115.89s 59.15s
Response Time (total) 290.43s 197.39s

Generation showcase

Hamster playing table tennis

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

#145 DeepSeek V3.2

none
Cost
$0.002
Time
7.0s
Tokens
1,046 tok

#152 Mistral Small 4

medium
Cost
$0.006
Time
47.9s
Tokens
9,857 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
DeepSeek V3.2 3.2 8.0 8.3% 1 9.35s 494 1,073 0
Mistral Small 4 5.6 3.8 66.7% 3 2.67s 708 4,055 4,778
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 3.1 6.9 11.1% 1 14.54s 7,279 4,528 0
Mistral Small 4 4.4 5.1 33.3% 2 39.98s 7,636 11,635 54,715
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 6.5 10.0 0.0% 0 115.89s 29,843 2,887 0
Mistral Small 4 3.0 10.0 0.0% 0 25.25s 18,706 2,612 10,700
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 6.3 5.8 66.7% 1 9.42s 7,890 1,710 0
Mistral Small 4 7.3 5.9 83.3% 1 1.23s 6,171 335 723
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 2.9 7.2 11.1% 1 4.17s 624 21 0
Mistral Small 4 5.3 7.2 44.4% 1 6.11s 742 2,621 6,904
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 4.7 1.6 66.7% 1 9.32s 314 43 0
Mistral Small 4 4.8 10.0 0.0% 0 2.05s 519 821 828
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 10.0 10.0 100.0% 0 1.52s 627 66 0
Mistral Small 4 7.3 5.8 83.3% 1 1.38s 729 540 1,031
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 7.6 7.2 77.8% 1 6.91s 424 298 0
Mistral Small 4 3.4 9.7 0.0% 0 2.17s 735 1,226 2,632
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 10.0 10.0 100.0% 0 11.85s 8,319 522 0
Mistral Small 4 10.0 10.0 100.0% 0 3.50s 6,420 321 810
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 3.0 10.0 0.0% 0 17.23s 183 17 0
Mistral Small 4 3.0 10.0 0.0% 0 5.92s 210 18 1,557

Quick Compare

Switch Comparison Pair