Skip to main content

Model comparison

DeepSeek V3.1 (Reasoning) vs Hy3 Preview

Data verified

Head-to-head evidence from 9 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

53.31/100
Margin
0.3pts
← winning
53/100
0 category wins0 category wins

Public leaderboard positions: DeepSeek V3.1 (Reasoning) #95 (Supported); Hy3 Preview unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek V3.1 (Reasoning) and Hy3 Preview share 9 comparable benchmark results. 0 of 8 categories are comparable. 4 results are unique to DeepSeek V3.1 (Reasoning); 13 to Hy3 Preview.

Updated July 17, 2026
Shared results
9
DeepSeek V3.1 (Reasoning) only
4
Hy3 Preview only
13
Comparable categories
0 / 8

Benchmark data for DeepSeek V3.1 (Reasoning) and Hy3 Preview is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 9 shared benchmark results across 3 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.

Hy3 Preview has the larger context window at 256K, compared with 128K for DeepSeek V3.1 (Reasoning).

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 V3.1 (Reasoning) and Hy3 Preview
CategoryDeepSeek V3.1 (Reasoning)ΔHy3 Preview
AgenticDeepSeek V3.1 (Reasoning)Not measuredMarginNo overlapHy3 Preview54.4
CodingDeepSeek V3.1 (Reasoning)Not measuredMarginNo overlapHy3 Preview57.8
KnowledgeDeepSeek V3.1 (Reasoning)Not measuredMarginNo overlapHy3 Preview33.8
Inst. FollowingDeepSeek V3.1 (Reasoning)Not measuredMarginNo overlapHy3 Preview63.1

Operational comparison

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

MetricDeepSeek V3.1 (Reasoning)Hy3 PreviewComparison
Input / output priceUSD per 1M tokensDeepSeek V3.1 (Reasoning)$0 input / $0 outputHy3 Preview$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondDeepSeek V3.1 (Reasoning)Not availableHy3 PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek V3.1 (Reasoning)Not availableHy3 PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek V3.1 (Reasoning)128KHy3 Preview256KHy3 Preview lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek V3.1 (Reasoning)Hy3 PreviewResult
τ²-bench resultsSource 37.4%Not comparable
Terminal-Bench 2.0Source 54.4%Not comparable
Gert LabsSource 36.91%Not comparable
AA Agentic IndexSource 30.7%Not comparable
GDPval-AASource 35.7%Not comparable
GDPval-AASource 1214Not comparable
Coding
BenchmarkDeepSeek V3.1 (Reasoning)Hy3 PreviewResult
Terminal-Bench HardSource 25.0%Not comparable
AA-SciCodeSource 39.1%47.6%Hy3 Preview leads
SWE-bench VerifiedSource 74.4%Not comparable
Terminal-Bench 2.0Source 54.4%Not comparable
SciCodeSource 41.2%Not comparable
AA Coding IndexSource 58.8%Not comparable
Reasoning
BenchmarkDeepSeek V3.1 (Reasoning)Hy3 PreviewResult
AA-LCRSource 53.3%66.7%Hy3 Preview leads
CritPtSource 2.0%4.9%Hy3 Preview leads
Knowledge
BenchmarkDeepSeek V3.1 (Reasoning)Hy3 PreviewResult
Artificial Analysis Intelligence IndexSource 20.7%41.2%Hy3 Preview leads
AA-GPQA DiamondSource 77.9%89.7%Hy3 Preview leads
AA-HLESource 13.0%31.6%Hy3 Preview leads
AA-Omniscience IndexSource -28.4%-18.5%Hy3 Preview leads
AA-Omniscience AccuracySource 28.8%31.5%Hy3 Preview leads
AA-Omniscience Hallucination RateSource 80.3%73.0%Hy3 Preview leads
GPQASource 87.2%Not comparable
GPQA-DSource 87.2%Not comparable
HLESource 25.5%Not comparable
Multimodal
BenchmarkDeepSeek V3.1 (Reasoning)Hy3 PreviewResult
Design Arena WebsiteSource 1157Not comparable
Inst. Following
BenchmarkDeepSeek V3.1 (Reasoning)Hy3 PreviewResult
AA-IFBenchSource 41.5%Not comparable
IFBenchSource 63.1%Not comparable
Frequently Asked Questions (3)

Can I compare DeepSeek V3.1 (Reasoning) and Hy3 Preview 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 V3.1 (Reasoning) and Hy3 Preview today?

DeepSeek V3.1 (Reasoning): $0.00 input / $0.00 output per 1M tokens Hy3 Preview: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 17, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.