Advertise here
#359

DeepSeek V3.2

DeepSeek Release: 2025-12-01 Tested on: 2026-10-01 02:45 deepseek/deepseek-v3.2::none
671B total (37B active)MoEOpen source
(medium) (none)

Summary

DeepSeek V3.2 scores 4.6 on AI BENCHY and ranks #359. It has 10.0 reliability, a 34.8% pass rate, $0.119 total cost, and 22.44s average response time.

What makes DeepSeek V3.2 unique: It stands out most in Instructions following, where it ranks #1, while Coding is its weakest area at #11.

Model facts

Researched on 2026-08-12

Reported
Parameters
671B total (37B active)
Architecture
MoE
Availability
Open source
License
MIT
Parameter source Availability source

Score

4.6

Consistency

8.2

Reliability

10.0

Total Cost (Current Price)

$0.119 ↑ +1.3%

Tested at: $0.117

Total Output Tokens

57,866

Total Input Tokens

342,158

Input Price

$0.280 / 1M

Output Price

$0.420 / 1M

Cache Read Price

$0.028 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 17

Attempt pass rate: 34.8%

Flaky tests

5

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

22.44s

Response Time (max): 122.50s

Response Time (total): 516.03s

Wrong answer: 9 API error: 3 Extra formatting: 2 Invalid tool call: 2 Did not follow instructions: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#359 DeepSeek V3.2

none
Cost
$0.002
Time
7.0s
Tokens
1,046 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 02:45 Re-test 4.6 10.0 $0.119 ↑ Current run
2026-07-16 23:15 New test added 5.0 10.0 $0.054 ↑ Compare
2026-06-04 14:22 New test added 5.2 10.0 $0.017 ↓ Compare
2026-05-22 00:35 Suite changed 5.6 10.0 $0.018 Compare
2026-05-08 15:31 Suite changed 5.7 10.0 $0.016 Compare
2026-04-20 17:48 First recorded run 6.1 N/A $0.016 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 Cache Read Price Cache Write Price
2026-06-04 15:40 $0.229 / 1M $0.344 / 1M N/A N/A
2026-07-10 11:30 $0.215 / 1M $0.322 / 1M N/A N/A
2026-08-14 12:51 $0.269 / 1M $0.400 / 1M N/A N/A
2026-10-01 18:33 $0.280 / 1M $0.420 / 1M $0.028 / 1M N/A

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

DeepSeek V3.2nonevsQwen3 Coder NextmediumDeepSeek V3.2nonevsGPT-5.4 NanononeDeepSeek V3.2nonevsGranite 4.2 8BhighDeepSeek V3.2nonevsLaguna S 2.1lowFree AvailableDeepSeek V3.2nonevsLaguna S 2.1noneFree AvailableDeepSeek V3.2nonevsNemotron 3.5 LightninglowFree AvailableDeepSeek V3.2nonevsNorth Mini CodedefaultFree AvailableDeepSeek V3.2nonevsLing 2.6 FlashdefaultDeepSeek V3.2nonevsNemotron 3.5 LightningmediumFree AvailableDeepSeek V3.2nonevsRing 2.6 1tdefault

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.0 10.0
Anti-AI Tricks 3.2 8.0
Coding 3.1 6.9
Combined 4.8 10.0
Data parsing and extraction 6.3 5.8
Domain specific 3.0 10.0
General Intelligence 4.7 1.6
Instructions following 10.0 10.0
Puzzle Solving 7.6 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models