AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#142

DeepSeek V4 Flash 0731

DeepSeek Release: 2026-08-01 Tested on: 2026-10-01 03:01 deepseek/deepseek-v4-flash-0731::medium
284B total (13B active)MoEClosed
(high) (medium) (low) (none)

Summary

DeepSeek V4 Flash 0731 scores 7.8 on AI BENCHY and ranks #142. It has 10.0 reliability, a 72.5% pass rate, $0.460 total cost, and 94.16s average response time.

Model facts

Researched on 2026-08-12

Reported
Parameters
284B total (13B active)
Architecture
MoE
Availability
Closed
License
-

Family size is reported; no exact public 0731 checkpoint was found.

Parameter source Availability source

Score

7.8

Consistency

7.2

Reliability

10.0

Total Cost (Current Price)

$0.460 ↑ +225.9%

Tested at: $0.142

Total Output Tokens

358,225

Total Input Tokens

274,189

Input Price

$0.005 / 1M

Output Price

$1.280 / 1M

Cache Read Price

$0.005 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 11

Attempt pass rate: 72.5%

Flaky tests

8

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

Response Time (avg)

94.16s

Response Time (max): 303.26s

Response Time (total): 2165.72s

Wrong answer: 5 No answer: 3 Extra formatting: 1 Invalid tool call: 1 Timed out: 1

Hamster playing table tennis

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

#142 DeepSeek V4 Flash 0731

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

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 03:01 Re-test 7.8 10.0 $0.460 ↑ Current run
2026-08-01 02:36 Initial run 7.3 9.8 $0.106 Compare

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

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 03:01 · Current run69/69 attempts7.87.210.012/238358,225274,189$0.46094.16s
2026-08-01 02:36 · Initial run66/66 attempts7.37.19.811/228618,41789,768$0.10685.80s
Difference—+0.5+0.1+0.2+10-260192+184421+$0.355+8358ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-08-02 09:23 $0.090 / 1M $0.180 / 1M N/A N/A
2026-08-11 09:41 $0.080 / 1M $0.180 / 1M N/A N/A
2026-08-14 12:51 $0.140 / 1M $0.280 / 1M N/A N/A
2026-10-06 16:43 $0.005 / 1M $1.280 / 1M $0.005 / 1M N/A

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 Flash 0731mediumvsGrok 4.5lowDeepSeek V4 Flash 0731mediumvsMuse WonderhighDeepSeek V4 Flash 0731mediumvsQwen3.7 PlusnoneDeepSeek V4 Flash 0731mediumvsGPT-6 LunahighDeepSeek V4 Flash 0731mediumvsGrok 4.6mediumDeepSeek V4 Flash 0731mediumvsMuse Glimmer 30BhighDeepSeek V4 Flash 0731mediumvsStep 3.7 FlashmediumDeepSeek V4 Flash 0731mediumvsNemotron 3.5 Super VLmediumFree AvailableDeepSeek V4 Flash 0731mediumvsGLM 5.3highDeepSeek V4 Flash 0731mediumvsClaude Haiku 5.5medium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
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 2.9 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