#254 DeepSeek V4 Flash 0731
none- Cost
- $0.004
- Time
- 198.4s
- Tokens
- 14,316 tok
Summary
DeepSeek V4 Flash 0731 scores 5.4 on AI BENCHY and ranks #254. It has 10.0 reliability, a 27.3% pass rate, $0.011 total cost, and 20.72s average response time.
What makes DeepSeek V4 Flash 0731 unique: It stands out most in Domain specific, where it ranks #2, while General Intelligence is its weakest area at #12.
Researched on 2026-08-12
Family size is reported; no exact public 0731 checkpoint was found.
5.4
Consistency
8.6
10.0
Total Output Tokens
25,426
Total Input Tokens
94,566
Input Price
$0.065 / 1M
Output Price
$0.180 / 1M
Flaky tests
4
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
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 | $0.011 ↓ | Current run | |
| 2026-08-01 02:35 Initial run | 5.4 | 10.0 | $0.021 | 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 |
|---|---|---|
| 2026-08-02 09:23 | $0.090 / 1M | $0.180 / 1M |
| 2026-08-11 09:41 | $0.080 / 1M | $0.180 / 1M |
| 2026-08-14 12:51 | $0.140 / 1M | $0.280 / 1M |
| 2026-09-08 21:53 | $0.065 / 1M | $0.180 / 1M |
Choose the first model, then click a second model to open a side-by-side page.
| 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 |