Skip to main content

Model comparison

Hy3 Preview vs SWE-1.7

Data verified

Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use BenchLM's provisional ranking lane.

54/100
Margin
20.0pts
winning →
Cognition
74/100
0 category wins1 category wins

Evidence parity. Hy3 Preview and SWE-1.7 share 2 comparable benchmark results. 1 of 8 categories are comparable. 20 results are unique to Hy3 Preview; 2 to SWE-1.7.

Updated July 14, 2026
Shared results
2
Hy3 Preview only
20
SWE-1.7 only
2
Comparable categories
1 / 8

Pick SWE-1.7 if you want the stronger benchmark profile. Hy3 Preview only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

SWE-1.7 is clearly ahead on the provisional aggregate, 74 to 54. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

SWE-1.7's sharpest advantage is in agentic, where it averages 81.5 against 54.4. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 54.4% to 81.5%.

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 Hy3 Preview and SWE-1.7
CategoryHy3 PreviewΔSWE-1.7
AgenticHy3 Preview54.4Margin 27.1SWE-1.781.5
CodingHy3 Preview61.6MarginNo overlapSWE-1.7Not measured
KnowledgeHy3 Preview33.8MarginNo overlapSWE-1.7Not measured
Inst. FollowingHy3 Preview63.1MarginNo overlapSWE-1.7Not measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Hy3 PreviewB · SWE-1.7
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 54.4%B 81.5%
    Winner: SWE-1.7Δ 27.1
    Terminal-Bench 2.0: Hy3 Preview scored 54.4%; SWE-1.7 scored 81.5%. SWE-1.7 wins this benchmark.

Operational comparison

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

MetricHy3 PreviewSWE-1.7Comparison
Input / output priceUSD per 1M tokensHy3 Preview$0 input / $0 outputSWE-1.7Not availableA complete price comparison is not available.
Generation speedtokens per secondHy3 PreviewNot availableSWE-1.7Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenHy3 PreviewNot availableSWE-1.7Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensHy3 Preview256KSWE-1.7256KListed context windows are equal.

Benchmark Deep Dive

AgenticSWE-1.7 wins
BenchmarkHy3 PreviewSWE-1.7Result
Terminal-Bench 2.0Source 54.4%81.5%SWE-1.7 leads
Gert LabsSource 36.91%Not comparable
AA Agentic IndexSource 30.7%Not comparable
GDPval-AASource 35.7%Not comparable
GDPval-AASource 1214Not comparable
Coding
BenchmarkHy3 PreviewSWE-1.7Result
SWE-bench VerifiedSource 74.4%Not comparable
Terminal-Bench 2.0Source 54.4%81.5%SWE-1.7 leads
SciCodeSource 41.2%Not comparable
AA-SciCodeSource 47.6%Not comparable
AA Coding IndexSource 58.8%Not comparable
FrontierCodeSource 42.3%Not comparable
SWE MultilingualSource 77.8%Not comparable
Reasoning
BenchmarkHy3 PreviewSWE-1.7Result
AA-LCRSource 66.7%Not comparable
CritPtSource 4.9%Not comparable
Knowledge
BenchmarkHy3 PreviewSWE-1.7Result
Artificial Analysis Intelligence IndexSource 41.2%Not comparable
GPQASource 87.2%Not comparable
GPQA-DSource 87.2%Not comparable
HLESource 25.5%Not comparable
AA-Omniscience AccuracySource 31.5%Not comparable
AA-Omniscience Hallucination RateSource 73.0%Not comparable
AA-GPQA DiamondSource 89.7%Not comparable
AA-HLESource 31.6%Not comparable
AA-Omniscience IndexSource -18.5%Not comparable
Inst. Following
BenchmarkHy3 PreviewSWE-1.7Result
IFBenchSource 63.1%Not comparable
Frequently Asked Questions (2)

Which is better, Hy3 Preview or SWE-1.7?

SWE-1.7 is ahead on BenchLM's provisional leaderboard, 74 to 54. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 54.4% and 81.5%.

Which is better for agentic tasks, Hy3 Preview or SWE-1.7?

SWE-1.7 has the edge for agentic tasks in this comparison, averaging 81.5 versus 54.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 14, 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.