AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#76

DeepSeek V4 Flash 0731

DeepSeek Release: 2026-08-01 Tested on: 2026-08-01 02:36 deepseek/deepseek-v4-flash-0731::medium
(high) (medium) (low) (none)

Summary

DeepSeek V4 Flash 0731 scores 7.3 on AI BENCHY and ranks #76. It has 9.8 reliability, a 72.7% pass rate, $0.106 total cost, and 85.80s average response time.

What makes DeepSeek V4 Flash 0731 unique: Its total benchmark cost is unusually low for its score range. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Score

7.3

Consistency

7.1

Total Output Tokens

618,417

Total Input Tokens

89,768

Input Price

$0.140 / 1M

Output Price

$0.280 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 72.7%

Flaky tests

8

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

Response Time (avg)

85.80s

Response Time (max): 288.78s

Response Time (total): 1887.69s

Hamster playing table tennis

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

#76 DeepSeek V4 Flash 0731

medium
Cost
$0.004
Time
93.3s
Tokens
13,252 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-01 02:47 $0.140 / 1M $0.280 / 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

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.2 7.9
Coding 6.4 4.4
Combined 7.3 5.8
Data parsing and extraction 10.0 10.0
Domain specific 3.6 7.2
General Intelligence 6.1 3.1
Instructions following 8.5 6.8
Puzzle Solving 8.2 7.3
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models