Compare / Kolibri-1 vs Qwen3-Coder-Next

Kolibri-1 vs Qwen3-Coder-Next

Updated November 2026

Verdict

Kolibri-1 scores higher on the Small LM Index: 71.1 vs 63.1. On the 6 benchmarks both labs report, Kolibri-1 wins 4 and Qwen3-Coder-Next wins 2. Both need about 50.6 GB of memory at 4-bit quantization. Only Qwen3-Coder-Next has a hosted API on OpenRouter ($0.29 per million tokens); the other has to be self-hosted.

Pick Kolibri-1 if…

you want the strongest model overall
you need precise instruction following
you work with long documents

Pick Qwen3-Coder-Next if…

you mostly write code
you want a hosted API rather than running it yourself
you want the more widely used model (more quantized builds and community support)

Specifications

	Kolibri-1	Qwen3-Coder-Next
Small LM Index	71.1 (likely 70–73)	63.1 (likely 54–70)
Lab	Aleph Alpha · Europe	Alibaba (Qwen) · China
Released	2026-10-03	2026-01-30
Parameters	78.1B (3.5B active, MoE)	79.7B (3B active, MoE)
Memory at 4-bit	~49.6 GB	~50.6 GB
Context window	1M tokens	262K tokens
Input	text	text
Reasoning	Always thinks	No thinking
License	Apache-2.0	Apache-2.0
API price / 1M tokens	Self-host only	$0.29 ($0.12 in, $0.80 out)
Hugging Face downloads (30 days)	21.4K	430.1K

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	Kolibri-1	Qwen3-Coder-Next
MMLU-Pro Knowledge	80.0	≈ 81
GPQA Diamond Knowledge	84.3	73.7^✓
Humanity's Last Exam Reasoning	21.5	10.1^✓
AIME Math	96.0	≈ 87
LiveCodeBench Coding	85.9	≈ 73
SWE-bench Verified Coding	66.4	70.6
Terminal-Bench Agentic	27.7	36.2
τ²-Bench Agentic	80.4	79.5^✓
IFBench Instruction following	78.1	35.2^✓
BFCL Agentic	61.4	—
AA-LCR Long context	—	47.0^✓
SciCode Coding	—	36.2^✓

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, Kolibri-1 or Qwen3-Coder-Next?

Kolibri-1 scores higher on the Small LM Index: 71.1 vs 63.1. On the 6 benchmarks both labs report, Kolibri-1 wins 4 and Qwen3-Coder-Next wins 2.

Which is cheaper to run?

Only Qwen3-Coder-Next has a hosted API on OpenRouter ($0.29 per million tokens); the other has to be self-hosted. Both need about 50.6 GB of memory at 4-bit quantization.

Which has the longer context window?

Kolibri-1 has the longer context window: 1M tokens against 262K.

Can I use Kolibri-1 and Qwen3-Coder-Next 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.