#74 DeepSeek V4 Flash 0731
high
No output was saved. The original provider response or failure reason is unavailable.
- Cost
- $0.000
- Time
- 187.3s
- Tokens
- 19,048 tok
DeepSeek
Release: 2026-08-01
Tested on: 2026-08-14 03:28
deepseek/deepseek-v4-flash-0731::high
284B total (13B active)MoEClosed
Summary
DeepSeek V4 Flash 0731 scores 8.0 on AI BENCHY and ranks #74. It has 10.0 reliability, a 75.8% pass rate, $0.084 total cost, and 114.94s average response time.
What makes DeepSeek V4 Flash 0731 unique: It stands out most in Combined, where it ranks #1, while Coding is its weakest area at #16. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
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.
8.0
Consistency
8.0
10.0
Total Output Tokens
513,307
Total Input Tokens
96,702
Input Price
$0.065 / 1M
Output Price
$0.180 / 1M
Flaky tests
5
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 03:28 Re-test | 8.0 | 10.0 | $0.084 ↓ | Current run | |
| 2026-08-01 02:40 Initial run | 8.0 | 9.6 | $0.123 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-14 03:28 · Current run | 66/66 attempts | 8.0 | 8.0 | 10.0 | 14/22 | 5 | 513,307 | 96,702 | $0.084 | 114.94s |
| 2026-08-01 02:40 · Initial run | 66/66 attempts | 8.0 | 7.8 | 9.6 | 14/22 | 6 | 544,164 | 96,609 | $0.123 | 110.77s |
| Difference | — | 0.0 | +0.2 | +0.4 | 0 | -1 | -30857 | +93 | -$0.040 | +4166ms |
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 |
|---|---|---|
| 2026-08-02 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 |
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 0731highvsDeepSeek V4 Flash 0731lowDeepSeek V4 Flash 0731highvsGLM 5.2highDeepSeek V4 Flash 0731highvsMuse Spark 1.1highDeepSeek V4 Flash 0731highvsInklingmediumDeepSeek V4 Flash 0731highvsInklinghighDeepSeek V4 Flash 0731highvsGPT-5.6 TerrahighDeepSeek V4 Flash 0731highvsMuse Glimmer 30BxhighDeepSeek V4 Flash 0731highvsKimi K3maxDeepSeek V4 Flash 0731highvsGPT-5 MinimediumDeepSeek V4 Flash 0731highvsGPT-5.2 Chatnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.7 | 7.9 | |
| Coding | 6.3 | 6.3 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.5 | 4.4 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 8.2 | 7.7 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |