#182 DeepSeek V4 Flash 0731
none- Cost
- $0.004
- Time
- 198.4s
- Tokens
- 14,316 tok
DeepSeek
Release: 2026-08-01
Tested on: 2026-08-01 02:35
deepseek/deepseek-v4-flash-0731::none
284B total (13B active)MoEClosed
Summary
DeepSeek V4 Flash 0731 scores 5.4 on AI BENCHY and ranks #182. It has 10.0 reliability, a 27.3% pass rate, $0.021 total cost, and 20.70s average response time.
Model facts
Researched on 2026-08-12
- Parameters
- 284B total (13B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Family size is reported; no exact public 0731 checkpoint was found.
5.4
Consistency
8.6
10.0
$0.021
Total Output Tokens
25,424
Total Input Tokens
94,557
Input Price
$0.140 / 1M
Output Price
$0.280 / 1M
Flaky tests
4
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 03:00 Re-test | 5.4 | 10.0 | $0.021 | Compare | |
| 2026-08-01 02:35 Initial run | 5.4 | 10.0 | $0.021 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-01 02:35 · Initial run | 66/66 attempts | 5.4 | 8.6 | 10.0 | 4/22 | 4 | 25,424 | 94,557 | $0.021 | 20.70s |
| 2026-08-14 03:00 · Re-test | 66/66 attempts | 5.4 | 8.6 | 10.0 | 4/22 | 4 | 25,426 | 94,566 | $0.021 | 20.72s |
| Difference | — | 0.0 | 0.0 | 0.0 | 0 | 0 | -2 | -9 | -$0.001 | -19ms |
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 |
|---|---|---|
| 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.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
DeepSeek V4 Flash 0731nonevsKimi K2.5noneDeepSeek V4 Flash 0731nonevsLaguna S 2.1highFree AvailableDeepSeek V4 Flash 0731nonevsMiMo-V2.5-PrononeDeepSeek V4 Flash 0731nonevsInkling SmallnoneDeepSeek V4 Flash 0731nonevsGPT-5.6 LunanoneDeepSeek V4 Flash 0731nonevsLaguna XS 2.1noneFree AvailableDeepSeek V4 Flash 0731nonevsKAT-Coder-Air V2.5lowDeepSeek V4 Flash 0731nonevsSeed-2.0-CodenoneDeepSeek V4 Flash 0731nonevsLaguna S 2.1mediumFree AvailableDeepSeek V4 Flash 0731nonevsLing-2.6-1Tnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.4 | 8.3 | |
| Coding | 4.3 | 10.0 | |
| Combined | 3.7 | 1.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 4.4 | 9.9 | |
| Instructions following | 5.0 | 6.8 | |
| Puzzle Solving | 3.2 | 9.9 | |
| Tool Calling | 9.5 | 10.0 | |
| Trivia | 3.0 | 10.0 |