Comparisons of Small Open Source AI Models (4B-40B)

Open source AI models with between 4B to 40B parameters.

Models are considered open source (also commonly referred to as open weights) where their weights are accessible to download. This allows self-hosting on your own infrastructure and enables customizing the model such as through fine-tuning.

For more details including relating to our methodology, see our FAQs.

Nanbeige logoNanbeige4.3-33B and Alibaba logoQwen3.8 27B (xhigh) score highest on the Artificial Analysis Progress Index v1 among Small open source models, defined as those with 4B-40B parameters, followed by Alibaba logoQwen3.8 27B (medium) & Alibaba logoQwen3.8 27B (low).
Artificial Analysis Openness Index · Higher is better
Artificial Analysis Progress Index v1 · Higher is better
Trainable parameters in billions

Openness

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Intelligence

Artificial Analysis Progress Index

Artificial Analysis Progress Index v1 is an item response theory estimate of general capability across Artificial Analysis evaluations

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100
See more

Agentic knowledge work, Elo

Agentic SaaS workflows

Agentic scientific research workflows in a terminal

Agentic software engineering in open-source repositories

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Physics reasoning

Quantitative analysis on spreadsheets & documents

Legal agentic work, Hallucination-Gated All-Pass Rate

No data available

Agentic business operations

Agentic real-world work tasks, Elo

Agentic interactive 3D experiences, Elo

No data available

Product and brand videos designed in code, Elo

Kubernetes incident root-cause analysis

Medical long context reasoning

Visual reasoning

Rich, varied, well-crafted language

Well-structured, scannable, answer-first

Truthful, acknowledges uncertainty, non-sycophantic

Use of filler and generic language

Size

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference (billions)

Progress Index vs. Active Parameters

Artificial Analysis Progress Index v1 · Active parameters at inference time (billions)
Most attractive quadrant
Pareto line

Progress Index vs. Total Parameters

Artificial Analysis Progress Index v1 · Size in parameters (billions)
Most attractive quadrant
Pareto line

Context Window

Context Window

Context window: tokens limit · Higher is better

Further details

Weights
Provider Benchmarks
Nanbeige4.3-33B
Nanbeige logoNanbeige
306
33B
524k
-
-
-
-
Qwen3.8 27B (Xhigh)
Alibaba logoAlibaba
303
27B
256k
$0.47
37.4
49
DeepInfraCoreWeaveAlibaba Cloud
+7
Qwen3.8 27B (Medium)
Alibaba logoAlibaba
290
27B
256k
$0.47
30.4
47
Alibaba Cloud
Qwen3.8 27B (Low)
Alibaba logoAlibaba
283
27B
256k
$0.47
28.7
47
Alibaba Cloud
K2 Horizon MoVA 36B A4B
Institute of Foundation Models logoInstitute of Foundation Models
281
36B
4B active at inference time
524k
-
-
-
-
Muse Glimmer (High)
Meta logoMeta
267
30B
131k
$0.23
4.8
90
Together AIDeepInfra
K2 Horizon 7B
Institute of Foundation Models logoInstitute of Foundation Models
263
7B
524k
-
-
-
-
Qwen3.8 27B (Non-reasoning)
Alibaba logoAlibaba
262
27B
256k
$0.47
18.5
40
Alibaba CloudMultiverse ComputingWafer
+4
Qwen3.6 35B A3B (Reasoning)
Alibaba logoAlibaba
261
36B
3B active at inference time
262k
$0.56
-
120
Alibaba CloudSiliconFlowDeepInfra
+5
G9v3-39A5B
AI9Stars logoAI9Stars
257
39B
5B active at inference time
131k
-
-
-
-
Gemma 4 31B (Reasoning)
Google logoGoogle
254
30.7B
256k
$0.00
-
36
CoreWeaveModularNovita
+7
Qwen3.6 35B A3B (Non-reasoning)
Alibaba logoAlibaba
246
36B
3B active at inference time
262k
$0.56
-
94
ScalewayCoreWeaveDeepInfra
+4