The AI arena is free today

Open Superagent

GLM-4.7 vs LFM2.5-VL-3B

Comparing GLM-4.7 and LFM2.5-VL-3B across benchmarks, pricing, and capabilities.

Zhipu AI · Liquid AI · Updated for 2026

Which is better?

GLM-4.7 and LFM2.5-VL-3B trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

Based on current benchmark, pricing, and model metadata for 2026.

Choose GLM-4.7

  • you want predictable pricing at $0.60/M input and $2.20/M output

Choose LFM2.5-VL-3B

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

At a glance

The differences that matter most.

GLM-4.7
Zhipu AI
LFM2.5-VL-3B
Liquid AI
Benchmark wins
—
—
Input price
$0.60 / M
— / M
Output price
$2.20 / M
— / M
Context window
202,800
—
Released
Dec 2025
Aug 2026
License
MIT
LFM Open License v1.0

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

GLM-4.7 and LFM2.5-VL-3Bdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

354.9B diff

GLM-4.7 has 354.9B more parameters than LFM2.5-VL-3B, making it 11361.6% larger.

Zhipu AI
GLM-4.7
358.0Bparameters
Liquid AI
LFM2.5-VL-3B
3.1Bparameters
358.0B
GLM-4.7
3.1B
LFM2.5-VL-3B

Context Window

Maximum input and output token capacity

Only GLM-4.7 specifies input context (202,800 tokens). Only GLM-4.7 specifies output context (131,072 tokens).

Zhipu AI
GLM-4.7
Input202,800 tokens
Output131,072 tokens
Liquid AI
LFM2.5-VL-3B
Input- tokens
Output- tokens
Tue Aug 25 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both GLM-4.7 and LFM2.5-VL-3B support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

GLM-4.7

Text
Images
Audio
Video

LFM2.5-VL-3B

Text
Images
Audio
Video

License

Usage and distribution terms

GLM-4.7 is licensed under MIT, while LFM2.5-VL-3B uses LFM Open License v1.0.

License differences may affect how you can use these models in commercial or open-source projects.

GLM-4.7

MIT

Open weights

LFM2.5-VL-3B

LFM Open License v1.0

Open weights

Release Timeline

When each model was launched

GLM-4.7 was released on 2025-12-22, while LFM2.5-VL-3B was released on 2026-08-12.

LFM2.5-VL-3B is 8 months newer than GLM-4.7.

GLM-4.7

Dec 22, 2025

8 months ago

LFM2.5-VL-3B

Aug 12, 2026

1 weeks ago

7mo 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 GLM-4.7 and LFM2.5-VL-3B side-by-side, then vote on the output you prefer.

GLM-4.7
✓ Preferred
LFM2.5-VL-3B
Open in Playground

FAQ

Common questions about GLM-4.7 vs LFM2.5-VL-3B.

Which is better, GLM-4.7 or LFM2.5-VL-3B?

GLM-4.7 (Zhipu AI) and LFM2.5-VL-3B (Liquid AI) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

How does GLM-4.7 compare to LFM2.5-VL-3B in benchmarks?

GLM-4.7 scores AIME 2025: 95.7%, Tau-bench: 87.4%, GPQA: 85.7%, LiveCodeBench v6: 84.9%, MMLU-Pro: 84.3%. LFM2.5-VL-3B scores DocVQA: 91.1%, POPE: 88.7%, RefCOCO-avg: 87.9%, TextVQA: 84.3%, OCRBench: 84.2%.

What are the context window sizes for GLM-4.7 and LFM2.5-VL-3B?

GLM-4.7 supports 203K tokens and LFM2.5-VL-3B 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 GLM-4.7 and LFM2.5-VL-3B?

Key differences include licensing (MIT vs LFM Open License v1.0). See the full comparison above for benchmark-by-benchmark results.

Who makes GLM-4.7 and LFM2.5-VL-3B?

GLM-4.7 is developed by Zhipu AI and LFM2.5-VL-3B is developed by Liquid AI.

Related comparisons