Compare / Nanbeige4.2 3B vs Spark-X2.5 4B

Nanbeige4.2 3B vs Spark-X2.5 4B

Updated November 2026

Verdict

Nanbeige4.2 3B scores higher on the Small LM Index: 70.4 vs 65.5. On the 5 benchmarks both labs report, Nanbeige4.2 3B wins 5 and Spark-X2.5 4B wins 0. Both need about 3.8 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.

Pick Nanbeige4.2 3B if…

you want the strongest model overall
you mostly write code
you need math and reasoning
you want the more widely used model (more quantized builds and community support)

Pick Spark-X2.5 4B if…

you work with long documents

Specifications

	Nanbeige4.2 3B	Spark-X2.5 4B
Small LM Index	70.4 (likely 69–72)	65.5 (likely 63–68)
Lab	Nanbeige (Kanzhun) · China	SparkLLM (XHToken) · China
Released	2026-07-21	2026-08-24
Parameters	4.2B (dense)	4.1B (dense)
Memory at 4-bit	~3.8 GB	~3.4 GB
Context window	262K tokens	1M tokens
Input	text	text
Reasoning	Always thinks	Hybrid (thinking on/off)
License	Apache-2.0	Apache-2.0
API price / 1M tokens	Self-host only	Self-host only
Hugging Face downloads (30 days)	120.3K	30.3K

Benchmarks

Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.

Benchmark	Nanbeige4.2 3B	Spark-X2.5 4B
GPQA Diamond Knowledge	87.4	73.7
Humanity's Last Exam Reasoning	17.8	12.3
AIME Math	≈ 93	90.7
LiveCodeBench Coding	72.5	≈ 75
SWE-bench Verified Coding	63.6	41.6
Terminal-Bench Agentic	44.1	—
τ²-Bench Agentic	—	75.1
IFBench Instruction following	—	75.0
IFEval Instruction following	—	93.0
BFCL Agentic	—	65.1
HMMT Math	82.8	81.2
AA-LCR Long context	58.7	56.3
SciCode Coding	—	34.7

Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.

Questions

Which is better, Nanbeige4.2 3B or Spark-X2.5 4B?

Nanbeige4.2 3B scores higher on the Small LM Index: 70.4 vs 65.5. On the 5 benchmarks both labs report, Nanbeige4.2 3B wins 5 and Spark-X2.5 4B wins 0.

Which is cheaper to run?

Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 3.8 GB of memory at 4-bit quantization.

Which has the longer context window?

Spark-X2.5 4B has the longer context window: 1M tokens against 262K.

Can I use Nanbeige4.2 3B and Spark-X2.5 4B commercially?

Both are released under the Apache-2.0 license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.