#119 DeepSeek V3.2
medium- Cost
- $0.001
- Time
- 53.6s
- Tokens
- 1,932 tok
DeepSeek
Release: 2025-12-01
Tested on: 2026-08-14 03:00
deepseek/deepseek-v3.2::medium
671B total (37B active)MoEOpen source
(medium)
(none)
Summary
DeepSeek V3.2 scores 7.0 on AI BENCHY and ranks #119. It has 10.0 reliability, a 65.2% pass rate, $0.078 total cost, and 68.43s average response time.
What makes DeepSeek V3.2 unique: It stands out most in Combined, where it ranks #3, while General Intelligence is its weakest area at #17.
Model facts
Researched on 2026-08-12
- Parameters
- 671B total (37B active)
- Architecture
- MoE
- Availability
- Open source
- License
- MIT
7.0
Consistency
7.4
10.0
Total Output Tokens
128,787
Total Input Tokens
101,056
Input Price
$0.269 / 1M
Output Price
$0.400 / 1M
Flaky tests
7
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 | 7.0 | 10.0 | $0.078 ↑ | Current run | |
| 2026-07-16 23:13 New test added | 7.0 | 10.0 | $0.078 ↑ | Compare | |
| 2026-06-04 14:41 New test added | 7.0 | 10.0 | $0.044 ↓ | Compare | |
| 2026-05-22 00:46 Suite changed | 7.0 | 9.1 | $0.037 | Compare | |
| 2026-05-08 15:27 Suite changed | 7.2 | 10.0 | $0.031 | Compare | |
| 2026-04-20 17:48 First recorded run | 8.0 | N/A | $0.029 | 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 03:00 · Current run | 66/66 attempts | 7.0 | 7.4 | 10.0 | 11/22 | 7 | 128,787 | 101,056 | $0.078 | 68.43s |
| 2026-06-04 14:41 · New test added | 63/63 attempts | 7.0 | 7.6 | 10.0 | 11/21 | 6 | 106,267 | 38,333 | $0.044 | 68.71s |
| Difference | — | 0.0 | -0.2 | 0.0 | 0 | +1 | +22520 | +62723 | +$0.034 | -272ms |
Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 63/63 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 |
|---|---|---|
| 2026-06-04 15:40 | $0.229 / 1M | $0.344 / 1M |
| 2026-07-10 11:30 | $0.215 / 1M | $0.322 / 1M |
| 2026-08-14 12:51 | $0.269 / 1M | $0.400 / 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 V3.2mediumvsGPT-5.6 SolnoneDeepSeek V3.2mediumvsGLM 5.1mediumDeepSeek V3.2mediumvsGrok 4.3mediumDeepSeek V3.2mediumvsGPT-5.5noneDeepSeek V3.2mediumvsSolar Pro 4highDeepSeek V3.2mediumvsMercury 2mediumDeepSeek V3.2mediumvsStep 3.7 FlashlowDeepSeek V3.2mediumvsGrok 4.20mediumDeepSeek V3.2mediumvsMuse Glimmer 30BlowDeepSeek V3.2mediumvsSeed-2.0-Minimedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.2 | 7.9 | |
| Coding | 6.0 | 7.2 | |
| Combined | 7.3 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 4.4 | |
| General Intelligence | 3.4 | 2.5 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 7.0 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |