Codesota · Models · DeepSeek-V3.2DeepSeek4 results · 1 benchmarks
Model card

DeepSeek-V3.2.

DeepSeekapi
§ 02 · Benchmarks

Every benchmark DeepSeek-V3.2 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01React Native EvalsMobile Development · React Native Code Generationasync-state-satisfaction77.7%#7/10—source ↗
02React Native EvalsMobile Development · React Native Code Generationrequirement-satisfaction69.0%#10/10—source ↗
03React Native EvalsMobile Development · React Native Code Generationnavigation-satisfaction75.7%#10/10—source ↗
04React Native EvalsMobile Development · React Native Code Generationanimation-satisfaction56.4%#10/10—source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where DeepSeek-V3.2 actually performs.

Mobile Development
1
benchmark
avg rank #9.3
§ 05 · Related models

Other DeepSeek models scored on Codesota.

DeepSeek R1
671B MoE params · 19 results
DeepSeek-V3
15 results
DeepSeek-V3.2
14 results
DeepSeek-V3.2-Speciale
11 results
DeepSeek-R1-0528
10 results
DeepSeek-Coder-V2-Instruct
Unknown params · 9 results
DeepSeek-v3-0324
9 results
DeepSeek-v3.1 (no thinking)
7 results
§ 06 · Sources & freshness

Where these numbers come from.

Callstack Incubator
4
results
4 of 4 rows marked verified.