Skip to main content

Model comparison

DeepSeek-R1 vs DeepSeek V3.2

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

DeepSeek
51.67/100
Margin
3.7pts
winning →
55.4/100
0 category wins0 category wins

Public leaderboard positions: DeepSeek-R1 #103 (Supported); DeepSeek V3.2 #82 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek-R1 and DeepSeek V3.2 share 11 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to DeepSeek-R1; 8 to DeepSeek V3.2.

Updated July 20, 2026
Shared results
11
DeepSeek-R1 only
0
DeepSeek V3.2 only
8
Comparable categories
0 / 8

Benchmark data for DeepSeek-R1 and DeepSeek V3.2 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

DeepSeek-R1 is priced at $0.55 input / $2.19 output per 1M tokens, versus $0.28 input / $0.42 output per 1M tokens for DeepSeek V3.2.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for DeepSeek-R1 and DeepSeek V3.2
CategoryDeepSeek-R1ΔDeepSeek V3.2
CodingDeepSeek-R1Not measuredMarginNo overlapDeepSeek V3.260.9
MathDeepSeek-R1Not measuredMarginNo overlapDeepSeek V3.217.1

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricDeepSeek-R1DeepSeek V3.2Comparison
Input / output priceUSD per 1M tokensDeepSeek-R1$0.55 input / $2.19 outputDeepSeek V3.2$0.28 input / $0.42 outputDeepSeek V3.2 has the lower combined listed price.
Generation speedtokens per secondDeepSeek-R1Not availableDeepSeek V3.235 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek-R1Not availableDeepSeek V3.23.75 sA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek-R1128KDeepSeek V3.2128KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek-R1DeepSeek V3.2Result
τ²-bench resultsSource 36.5%78.9%DeepSeek V3.2 leads
Claw-EvalSource 40.2%Not comparable
VITA-BenchSource 18.5%Not comparable
Gert LabsSource 29.57%Not comparable
Coding
BenchmarkDeepSeek-R1DeepSeek V3.2Result
AA-SciCodeSource 40.3%38.7%DeepSeek-R1 leads
SWE-RebenchSource 60.9%Not comparable
React Native EvalsSource 71.5%Not comparable
Reasoning
BenchmarkDeepSeek-R1DeepSeek V3.2Result
AA-LCRSource 54.7%39.0%DeepSeek-R1 leads
CritPtSource 1.4%0.9%DeepSeek-R1 leads
Knowledge
BenchmarkDeepSeek-R1DeepSeek V3.2Result
Artificial Analysis Intelligence IndexSource 20.1%24.7%DeepSeek V3.2 leads
AA-GPQA DiamondSource 81.3%75.1%DeepSeek-R1 leads
AA-HLESource 14.9%10.5%DeepSeek-R1 leads
AA-Omniscience IndexSource -27.1%-46.7%DeepSeek-R1 leads
AA-Omniscience AccuracySource 31.0%24.2%DeepSeek-R1 leads
AA-Omniscience Hallucination RateSource 84.0%93.5%DeepSeek-R1 leads
Math
BenchmarkDeepSeek-R1DeepSeek V3.2Result
FrontierMath v2 (Tiers 1-3)Source 22.100%Not comparable
FrontierMath v2 (Tier 4)Source 2.100%Not comparable
Multimodal
BenchmarkDeepSeek-R1DeepSeek V3.2Result
Design Arena WebsiteSource 1206Not comparable
Inst. Following
BenchmarkDeepSeek-R1DeepSeek V3.2Result
AA-IFBenchSource 39.6%49.0%DeepSeek V3.2 leads
Frequently Asked Questions (3)

Can I compare DeepSeek-R1 and DeepSeek V3.2 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for DeepSeek-R1 and DeepSeek V3.2 today?

DeepSeek-R1: $0.55 input / $2.19 output per 1M tokens DeepSeek V3.2: $0.28 input / $0.42 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

DeepSeek-R1
API / mo$2,055
Self-host / mo$18,221
Break-even583M/day
DeepSeek V3.2
API / mo$525
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.