The AI arena is free today

Open Superagent

Hy3 vs Inkling-Small

Hy3 and Inkling-Small are closely matched at 42.9 and 39.3 on the LLM Stats Score.

Tencent · Thinking Machines Lab · Updated for 2026

Which is better?

Hy3 and Inkling-Small are closely matched on the overall LLM Stats Score at 42.9 and 39.3.

In the 7 individual benchmarks reported for both models, Hy3 wins 4; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Hy3

  • you value its reported benchmark strengths — it wins 4 of 7 exact shared results

Choose Inkling-Small

  • you want the most recent training data — it shipped Jul 2026

At a glance

The differences that matter most.

Core performance indexes
42.9
#39
39.3
#53
42.9
#37
39.0
#52
35.0
#27
31.1
#45
28.2
#36
24.8
#45
Cost, coverage & limits
Benchmark wins
4 of 7
3 of 7
Input price
— / M
$0.30 / M
Output price
— / M
$1.20 / M
Context window
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Hy3
Inkling-Small
34.6#43
34.2#46
23.2#39
23.3#38
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

31 reported for Hy3 · 24 for Inkling-Small

7 shared

Hy3 outperforms in 4 benchmarks (BrowseComp, GPQA, SWE-Bench Pro, Terminal-Bench 2.1), while Inkling-Small is better at 3 benchmarks (MCP Atlas, SWE-Bench Verified, Toolathlon).

Hy3 has a slight edge in benchmark performance.

Fri Aug 28 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

19.0B diff

Hy3 has 19.0B more parameters than Inkling-Small, making it 6.9% larger.

Tencent
Hy3
295.0Bparameters
Thinking Machines Lab
Inkling-Small
276.0Bparameters
295.0B
Hy3
276.0B
Inkling-Small

Context Window

Maximum input and output token capacity

Only Inkling-Small specifies input context (256,000 tokens). Only Inkling-Small specifies output context (256,000 tokens).

Tencent
Hy3
Input- tokens
Output- tokens
Thinking Machines Lab
Inkling-Small
Input256,000 tokens
Output256,000 tokens
Fri Aug 28 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Inkling-Small supports multimodal inputs, whereas Hy3 does not.

Inkling-Small can handle both text and other forms of data like images, making it suitable for multimodal applications.

Hy3

Text
Images
Audio
Video

Inkling-Small

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Hy3

Apache 2.0

Open weights

Inkling-Small

Apache 2.0

Open weights

Release Timeline

When each model was launched

Hy3 was released on 2026-07-06, while Inkling-Small was released on 2026-07-30.

Inkling-Small is 1 month newer than Hy3.

Hy3

Jul 6, 2026

1 months ago

Inkling-Small

Jul 30, 2026

4 weeks ago

3w newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Hy3 and Inkling-Small side-by-side, then vote on the output you prefer.

Hy3
✓ Preferred
Inkling-Small
Open in Playground

FAQ

Common questions about Hy3 vs Inkling-Small.

Which is better, Hy3 or Inkling-Small?

Hy3 and Inkling-Small are closely matched on the LLM Stats Score at 42.9 and 39.3. Hy3 is made by Tencent and Inkling-Small is made by Thinking Machines Lab. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Hy3 compare to Inkling-Small in benchmarks?

Hy3 scores DeepSearchQA: 91.0%, GPQA: 90.4%, IMO-AnswerBench: 90.0%, BrowseComp: 84.2%, MCP Atlas: 79.1%. Inkling-Small scores AIME 2026: 95.5%, VoiceBench Avg: 90.1%, GPQA: 89.5%, Global-MMLU-Lite: 86.7%, ARC-AGI: 84.0%.

What are the context window sizes for Hy3 and Inkling-Small?

Hy3 supports an unknown number of tokens and Inkling-Small supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Hy3 and Inkling-Small?

Key differences include LLM Stats Score (42.9 vs 39.3), multimodal support (no vs yes). See the full comparison above for benchmark-by-benchmark results.

Who makes Hy3 and Inkling-Small?

Hy3 is developed by Tencent and Inkling-Small is developed by Thinking Machines Lab.