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

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs Gemini 3 PRO Preview

Summary

DeepSeek V4 Pro vs Gemini 3 PRO Preview benchmark comparison: DeepSeek V4 Pro leads on average score with 7.6 vs 6.2. DeepSeek V4 Pro has the lower benchmark cost at $0.157 vs $0.385. Gemini 3 PRO Preview is faster at 9.05s vs 77.20s, with pass rates of 66.7% vs 66.7%.

Recommended model: DeepSeek V4 Pro - It has the best score here (7.6), while costing about 2.5x less than Gemini 3 PRO Preview.

Last updated at: 2026-06-18

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Gemini 3 PRO Preview Gemini 3 PRO Preview medium Release: 2025-11-18
Score 7.6 6.2
Rank #41 #91
Reliability 9.3 N/A
Consistency 7.0 10.0
Tests Correct
Attempt pass rate 66.7% 66.7%
Flaky tests 8 0
Total Runs 63 63
Cost per result 1.742 1.406
Total Cost $0.157 $0.385
Input Price $0.435 / 1M $9.506 / 1M
Output Price $0.870 / 1M $9.506 / 1M
Total Input Tokens 38,726 28,848
Output Tokens 6,334 1,490
Reasoning Tokens 159,151 10,102
Response Time (avg) 77.20s 9.05s
Response Time (max) 416.76s 26.24s
Response Time (total) 1621.17s 90.53s

Generation showcase

Hamster playing table tennis

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

#41 DeepSeek V4 Pro

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

#91 Gemini 3 PRO Preview

medium
No endpoints found for google/gemini-3-pro-preview.
Cost
$0.000
Time
0.1s
Tokens
0 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 V4 Pro 5.7 5.9 58.3% 2 25.70s 536 149 3,214
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 14.99s 500 149 1,485
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.1 4.6 66.7% 2 243.00s 5,090 383 84,580
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 38.17s 14,060 454 5,836
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 10.37s 13,211 351 952
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 25.03s 7,690 274 2,166
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 10.84s 7,259 279 3,156
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.6 7.2 22.2% 1 151.46s 569 4,404 50,391
Gemini 3 PRO Preview 5.3 10.0 33.3% 0 7.01s 643 15 1,195
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 8.83s 471 115 1,013
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 9.34s 486 78 374
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 7.8 6.6 83.3% 1 8.73s 627 66 2,726
Gemini 3 PRO Preview 9.8 10.0 100.0% 0 3.26s 623 69 754
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.9 4.9 77.8% 2 56.85s 591 178 2,563
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 3.88s 570 225 1,215
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 9.8 10.0 100.0% 0 15.92s 8,909 295 701
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 11.96s 5,556 324 971
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.0 10.0 0.0% 0 34.01s 183 16 5,961
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0 0

Quick Compare

Switch Comparison Pair