AI BENCHY
Advertise here

#69

DeepSeek V3.2

DeepSeek Release: 2025-12-01 Tested on: 2026-04-20 17:48 deepseek/deepseek-v3.2::none
(medium) (none)

Score

6.1

Consistency

8.1

Reliability

N/A

Total Cost (Current Price)

$0.016

Total Output Tokens

8,384

Input Price

$0.252 / 1M

Output Price

$0.378 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 50.0%

Flaky tests

4

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

Response Time (avg)

12.09s

Response Time (max): 115.89s

Response Time (total): 217.56s

Wrong answer: 8 Extra formatting: 2 Invalid tool call: 1

Run history

Tested on Score Reliability Tests Correct Total Cost 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 Current run

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal CostResponse Time (avg)
2026-04-20 17:48 · First recorded run6.18.1N/A7/1848,384$0.01612.09s
2026-05-08 15:31 · Suite changed5.77.910.07/1957,194$0.01613.43s
Difference+0.5+0.20-1+1190+$0.001-1340ms

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.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

DeepSeek V3.2nonevsNemotron 3 SupermediumFree AvailableDeepSeek V3.2nonevsQwen3.5-FlashnoneDeepSeek V3.2nonevsDeepSeek V4 PrononeDeepSeek V3.2nonevsGLM 5V TurbononeDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsSeed-2.0-LitenoneDeepSeek V3.2nonevsGemini 3 Flash PreviewmediumDeepSeek V3.2nonevsGemini 3.5 FlashhighDeepSeek V3.2nonevsRing-2.6-1TmediumDeepSeek V3.2nonevsGemini 3.5 Flashlow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.2 9.8
Coding 2.4 1.3
Combined 6.5 10.0
Data parsing and extraction 6.3 5.8
Domain specific 3.6 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 8.5 7.5
Tool Calling 10.0 10.0

Compared models