#55 DeepSeek V4 Flash
high- Cost
- $0.003
- Time
- 93.1s
- Tokens
- 7,926 tok
DeepSeek
Release: 2026-04-24
Tested on: 2026-05-22 00:39
deepseek/deepseek-v4-flash::high
(high)
(none)
Summary
DeepSeek V4 Flash scores 7.4 on AI BENCHY and ranks #55. It has 10.0 reliability, a 71.7% pass rate, $0.038 total cost, and 46.28s average response time.
What makes DeepSeek V4 Flash unique: It stands out most in Data parsing and extraction, where it ranks #1, while Domain specific is its weakest area at #13.
7.4
Consistency
8.0
10.0
$0.038
Total Output Tokens
126,869
Total Input Tokens
0
Input Price
$0.112 / 1M
Output Price
$0.224 / 1M
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Generation showcase
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 |
|---|---|---|---|---|---|
| 2026-06-04 14:24 Re-test | 7.7 | 10.0 | $0.029 ↓ | Compare | |
| 2026-06-04 13:02 New test added | 7.7 | 10.0 | $0.028 ↓ | Compare | |
| 2026-05-22 00:39 Suite changed | 7.4 | 10.0 | $0.038 | Current run | |
| 2026-04-25 21:41 Re-test | 7.8 | N/A | $0.031 | Compare | |
| 2026-04-24 09:19 Initial run | 7.8 | N/A | $0.019 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|
| 2026-05-22 00:39 · Suite changed | 7.4 | 8.0 | 10.0 | 11/20 | 5 | 126,869 | 0 | $0.038 | 46.28s |
| 2026-04-25 21:41 · Re-test | 7.8 | 7.8 | N/A | 11/18 | 5 | 92,064 | 0 | $0.031 | 45.41s |
| Difference | -0.4 | +0.2 | 0 | 0 | +34805 | 0 | +$0.007 | +872ms |
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
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 FlashhighFree AvailablevsGemma 4 31BmediumFree AvailableDeepSeek V4 FlashhighFree AvailablevsQwen3.5-122B-A10BmediumDeepSeek V4 FlashhighFree AvailablevsQwen3.6 PlusmediumDeepSeek V4 FlashhighFree AvailablevsQwen3.5-27BmediumDeepSeek V4 FlashhighFree AvailablevsQwen3.5 Plus 2026-02-15mediumDeepSeek V4 FlashhighFree AvailablevsGemini 3 Flash PreviewmediumDeepSeek V4 FlashhighFree AvailablevsGemini 3.5 FlashhighDeepSeek V4 FlashhighFree AvailablevsNemotron 3 Ultra 550b A55bmediumFree AvailableDeepSeek V4 FlashhighFree AvailablevsGemini 3.5 Flashlow
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.3 | 10.0 | |
| Coding | 6.8 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 4.1 | 4.4 | |
| General Intelligence | 6.1 | 3.1 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 6.4 | 4.4 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |