The AI arena is free today

Open Superagent

Beam 1.0 vs Hy4 preview

Hy4 preview leads the LLM Stats Score 49.6 to 44.6.

Reflection AI · Tencent · Updated for 2026

Which is better?

Hy4 preview leads the overall LLM Stats Score 49.6 to 44.6, ranking #23 overall.

In the 7 individual benchmarks reported for both models, Hy4 preview wins 5; 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 Beam 1.0

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

Choose Hy4 preview

  • overall performance matters — it scores 49.6 and ranks #23 on LLM Stats
  • you value its reported benchmark strengths — it wins 5 of 7 exact shared results

At a glance

The differences that matter most.

Beam 1.0
Reflection AI
Hy4 preview
Tencent
Core performance indexes
LLM Stats Score
44.6
#46
49.6
#23
Reasoning
45.5
#37
49.8
#15
Coding
33.7
#39
37.0
#26
Agents
28.8
#53
34.8
#27
Cost, coverage & limits
Benchmark wins
2 of 7
5 of 7
Input price
$0.40 / M
— / M
Output price
$1.20 / M
— / M
Context window
1,048,576
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Beam 1.0
Hy4 preview
Math
35.1#45
38.5#26
Tool use
26.4#32
28.9#20
Research
19.0#27
27.5#8
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

22 reported for Beam 1.0 · 32 for Hy4 preview

7 shared

Beam 1.0 outperforms in 2 benchmarks (AutomationBench, SWE-Bench Pro), while Hy4 preview is better at 5 benchmarks (CritPT, GPQA, MCP Atlas, SWE-bench Multilingual, Terminal-Bench 2.1).

Hy4 preview shows notably better performance in the majority of benchmarks.

Thu Oct 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

268.7B diff

Hy4 preview has 268.7B more parameters than Beam 1.0, making it 53.6% larger.

Reflection AI
Beam 1.0
501.3Bparameters
Tencent
Hy4 preview
770.0Bparameters
501.3B
Beam 1.0
770.0B
Hy4 preview

Context Window

Maximum input and output token capacity

Only Beam 1.0 specifies input context (1,048,576 tokens). Only Beam 1.0 specifies output context (131,072 tokens).

Reflection AI
Beam 1.0
Input1,048,576 tokens
Output131,072 tokens
Tencent
Hy4 preview
Input- tokens
Output- tokens
Thu Oct 22 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

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

Beam 1.0

Apache 2.0

Open weights

Hy4 preview

Apache 2.0

Open weights

Release Timeline

When each model was launched

Beam 1.0 was released on 2026-10-16, while Hy4 preview was released on 2026-08-28.

Beam 1.0 is 2 months newer than Hy4 preview.

Beam 1.0

Oct 16, 2026

4 days ago

1mo newer
Hy4 preview

Aug 28, 2026

1 months ago

Knowledge Cutoff

When training data ends

Beam 1.0 has a documented knowledge cutoff of 2026-06-30, while Hy4 preview's cutoff date is not specified.

We can confirm Beam 1.0's training data extends to 2026-06-30, but cannot make a direct comparison without Hy4 preview's cutoff date.

Beam 1.0

Jun 2026

Hy4 preview

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Beam 1.0 and Hy4 preview side-by-side, then vote on the output you prefer.

Beam 1.0
✓ Preferred
Hy4 preview
Open in Playground

FAQ

Common questions about Beam 1.0 vs Hy4 preview.

Which is better, Beam 1.0 or Hy4 preview?

Hy4 preview leads the LLM Stats Score 49.6 to 44.6. Beam 1.0 is made by Reflection AI and Hy4 preview is made by Tencent. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Beam 1.0 compare to Hy4 preview in benchmarks?

Beam 1.0 scores AIME 2026: 97.7%, GPQA: 90.6%, LiveCodeBench: 88.3%, SWE-Bench Verified: 81.6%, MCP Atlas: 80.8%. Hy4 preview scores GPQA: 92.3%, Terminal-Bench 2.1: 85.4%, WideSearch: 83.9%, MCP Atlas: 83.7%, SWE-bench Multilingual: 82.9%.

What are the context window sizes for Beam 1.0 and Hy4 preview?

Beam 1.0 supports 1.0M tokens and Hy4 preview supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Beam 1.0 and Hy4 preview?

Key differences include LLM Stats Score (44.6 vs 49.6). See the full comparison above for benchmark-by-benchmark results.

Who makes Beam 1.0 and Hy4 preview?

Beam 1.0 is developed by Reflection AI and Hy4 preview is developed by Tencent.

Related comparisons