AI BENCHY
Advertise here
#113

DeepSeek V4 Pro

DeepSeek Release: 2026-04-24 Tested on: 2026-06-04 14:24 deepseek/deepseek-v4-pro::none
(high) (none)

Summary

DeepSeek V4 Pro scores 5.7 on AI BENCHY and ranks #113. It has 8.5 reliability, a 42.9% pass rate, $0.025 total cost, and 12.38s average response time.

What makes DeepSeek V4 Pro unique: It stands out most in Combined, where it ranks #2, while Data parsing and extraction is its weakest area at #10.

Score

5.7

Consistency

8.5

Reliability

8.5

Total Cost (Current Price)

$0.025 ↓ -47.7%

Tested at: $0.047

Total Output Tokens

5,349

Total Input Tokens

44,845

Input Price

$0.435 / 1M

Output Price

$0.870 / 1M

Tests Correct

Wrong Tests: 14

Attempt pass rate: 42.9%

Flaky tests

4

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

12.38s

Response Time (max): 58.65s

Response Time (total): 260.06s

Wrong answer: 10 Did not follow instructions: 2 API error: 1 Extra formatting: 1

Generation showcase

Hamster playing table tennis

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

#113 DeepSeek V4 Pro

none
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 14:24 New test added 5.7 8.5 $0.025 ↓ Current run
2026-05-22 00:38 Suite changed 6.0 8.1 $0.046 Compare
2026-04-29 14:46 Re-test 6.2 7.9 $0.043 Compare
2026-04-24 09:19 Initial run 3.1 N/A $0.009 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $0.435 / 1M $0.870 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

DeepSeek V4 PrononevsGPT-5.5noneDeepSeek V4 PrononevsGemini 3.1 Flash LitenoneDeepSeek V4 PrononevsGPT-5 NanomediumDeepSeek V4 PrononevsQwen3.5 Plus 2026-02-15noneDeepSeek V4 PrononevsGemini 3 Flash PreviewmediumDeepSeek V4 PrononevsGemini 3.5 FlashhighDeepSeek V4 PrononevsNemotron 3 Ultra 550b A55bmediumFree AvailableDeepSeek V4 PrononevsGemini 3.5 Flashlow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.5 8.0
Coding 4.6 7.9
Combined 9.5 10.0
Data parsing and extraction 6.9 5.8
Domain specific 5.3 10.0
General Intelligence 4.3 9.9
Instructions following 6.3 10.0
Puzzle Solving 7.6 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models