Skip to main content

Model comparison

Hy3 Preview vs Inkling

Data verified

Head-to-head evidence from 7 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

53/100
Margin
16.0pts
winning →
Thinking Machines Lab
69/100
0 category wins4 category wins

Verified leaderboard positions: Hy3 Preview unranked; Inkling #17

Evidence parity. Hy3 Preview and Inkling share 7 comparable benchmark results. 4 of 8 categories are comparable. 15 results are unique to Hy3 Preview; 9 to Inkling.

Updated July 15, 2026
Shared results
7
Hy3 Preview only
15
Inkling only
9
Comparable categories
4 / 8

Pick Inkling if you want the stronger benchmark profile. Hy3 Preview only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 7 shared benchmark results across 4 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Inkling is clearly ahead on the provisional aggregate, 69 to 53. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Inkling's sharpest advantage is in knowledge, where it averages 51.7 against 33.8. The single biggest benchmark swing on the page is HLE, 25.5% to 46%.

Inkling is also the more expensive model on tokens at $1.87 input / $4.68 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Hy3 Preview. That is roughly Infinityx on output cost alone. Hy3 Preview is the reasoning model in the pair, while Inkling is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Inkling gives you the larger context window at 1M, compared with 256K for Hy3 Preview.

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 Inkling
CategoryHy3 PreviewΔInkling
KnowledgeHy3 Preview33.8Margin 17.9Inkling51.7
Inst. FollowingHy3 Preview63.1Margin 16.7Inkling79.8
AgenticHy3 Preview54.4Margin 15.0Inkling69.4
CodingHy3 Preview57.8Margin 10.8Inkling68.6
MathHy3 PreviewNot measuredMarginNo overlapInkling97.1
MultimodalHy3 PreviewNot measuredMarginNo overlapInkling76.5

Decisive benchmark drivers

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

More
A · Hy3 PreviewB · Inkling
  1. HLE

    Knowledge
    Source ↗
    A 25.5%B 46%
    Winner: InklingΔ 20.5
    HLE: Hy3 Preview scored 25.5%; Inkling scored 46%. Inkling wins this benchmark.
  2. IFBench

    Inst. Following
    Source ↗
    A 63.1%B 79.8%
    Winner: InklingΔ 16.7
    IFBench: Hy3 Preview scored 63.1%; Inkling scored 79.8%. Inkling wins this benchmark.
  3. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 54.4%B 63.8%
    Winner: InklingΔ 9.4
    Terminal-Bench 2.0: Hy3 Preview scored 54.4%; Inkling scored 63.8%. Inkling wins this benchmark.
  4. SWE-bench Verified

    Coding
    Source ↗
    A 74.4%B 77.6%
    Winner: InklingΔ 3.2
    SWE-bench Verified: Hy3 Preview scored 74.4%; Inkling scored 77.6%. Inkling wins this benchmark.
  5. GPQA

    Knowledge
    Source ↗
    A 87.2%B 87.9%
    Winner: InklingΔ 0.7
    GPQA: Hy3 Preview scored 87.2%; Inkling scored 87.9%. Inkling wins this benchmark.

Operational comparison

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

MetricHy3 PreviewInklingComparison
Input / output priceUSD per 1M tokensHy3 Preview$0 input / $0 outputInkling$1.87 input / $4.68 outputHy3 Preview has the lower combined listed price.
Generation speedtokens per secondHy3 PreviewNot availableInklingNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenHy3 PreviewNot availableInklingNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensHy3 Preview256KInkling1MInkling lists the larger context window.

Benchmark Deep Dive

AgenticInkling wins
BenchmarkHy3 PreviewInklingResult
Terminal-Bench 2.0Source 54.4%63.8%Inkling leads
Gert LabsSource 36.91%Not comparable
AA Agentic IndexSource 30.7%Not comparable
GDPval-AASource 35.7%Not comparable
GDPval-AASource 1214Not comparable
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
CodingInkling wins
BenchmarkHy3 PreviewInklingResult
SWE-bench VerifiedSource 74.4%77.6%Inkling leads
Terminal-Bench 2.0Source 54.4%63.8%Inkling leads
SciCodeSource 41.2%Not comparable
AA-SciCodeSource 47.6%Not comparable
AA Coding IndexSource 58.8%Not comparable
SWE-bench ProSource 54.3%Not comparable
Reasoning
BenchmarkHy3 PreviewInklingResult
AA-LCRSource 66.7%Not comparable
CritPtSource 4.9%Not comparable
KnowledgeInkling wins
BenchmarkHy3 PreviewInklingResult
Artificial Analysis Intelligence IndexSource 41.2%Not comparable
GPQASource 87.2%87.9%Inkling leads
GPQA-DSource 87.2%87.9%Inkling leads
HLESource 25.5%46%Inkling leads
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
HLE w/o toolsSource 30%Not comparable
Math
BenchmarkHy3 PreviewInklingResult
AIME26Source 97.1%Not comparable
Multimodal
BenchmarkHy3 PreviewInklingResult
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
Inst. FollowingInkling wins
BenchmarkHy3 PreviewInklingResult
IFBenchSource 63.1%79.8%Inkling leads
Frequently Asked Questions (5)

Which is better, Hy3 Preview or Inkling?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 53. The biggest single separator in this matchup is HLE, where the scores are 25.5% and 46%.

Which is better for knowledge tasks, Hy3 Preview or Inkling?

Inkling has the edge for knowledge tasks in this comparison, averaging 51.7 versus 33.8. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Hy3 Preview or Inkling?

Inkling has the edge for coding in this comparison, averaging 68.6 versus 57.8. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Hy3 Preview or Inkling?

Inkling has the edge for agentic tasks in this comparison, averaging 69.4 versus 54.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for instruction following, Hy3 Preview or Inkling?

Inkling has the edge for instruction following in this comparison, averaging 79.8 versus 63.1. Inside this category, IFBench is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 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.