Comparison of Open Source Models

Comparison and analysis of open source AI models across key performance metrics including quality, performance, inference speed, context window, parameter count & licensing details.

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 relating to our methodology, see our FAQs.

Kimi logoKimi K3.1 Pro and DeepSeek logoDeepSeek V4.1 Flash 1017 (max) are the highest intelligence open source models, followed by Z AI logoGLM-5.3 (max) & Thinking Machines logoInkling 2 Small.
Artificial Analysis Openness Index · Higher is better
Artificial Analysis Intelligence Index · 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)

Open Source Progress

Open Weights vs. Proprietary: Artificial Analysis Progress Index, Over Time

Artificial Analysis Progress Index v1 is an item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown
Nov 2022Nov 2026

Open Source: Artificial Analysis Progress Index by Lab, Over Time

Artificial Analysis Progress Index v1 is an item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown

Open Source: Artificial Analysis Progress Index by Size, Over Time

Artificial Analysis Progress Index v1 is an item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

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

Agentic business operations

Agentic real-world work tasks, Elo

Agentic interactive 3D experiences, Elo

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

Intelligence Index By Model Size

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Model Size: Total and Active Parameters

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

Intelligence Index vs. Active Parameters

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

Intelligence Index vs. Total Parameters

Artificial Analysis Intelligence Index · 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
Kimi K3.1 Pro
Kimi logoKimi
46
2.8T
104B active at inference time
1M
$1.54
38.8
31
DatabricksIncoKimi
+15
DeepSeek V4.1 Flash 1017 (Max)
DeepSeek logoDeepSeek
33
552B
16B active at inference time
1M
$0.18
13.1
177
BasetenNovitaBaseten
+23
GLM-5.3 (Max)
Z AI logoZ AI
32
753B
40B active at inference time
1M
$0.90
22.2
89
ModalZaiSambaNova
+26
Inkling 2 Small
Thinking Machines logoThinking Machines
31
594B
17B active at inference time
1M
$0.18
21.6
116
DeepInfraNebiusTogether AIThinking Machines
MiMo-V2.6-Pro
Xiaomi logoXiaomi
30
1T
42B active at inference time
1M
$0.18
37.1
54
XiaomiDeepInfraPrimaLabsGMI
Ling 3.1 Flash 1019
InclusionAI logoInclusionAI
30
560B
25B active at inference time
1M
$0.19
-
-
InclusionAI
Mistral Large 4 (High)
Mistral logoMistral
26
1.1T
52B active at inference time
1M
$0.40
18.0
76
Mistral
Qwen3.8 27B (Xhigh)
Alibaba logoAlibaba
20
27B
256k
$0.47
37.4
49
DeepInfraCoreWeaveAlibaba Cloud
+7
K2 Horizon 375B A23B
Institute of Foundation Models logoInstitute of Foundation Models
18
375B
23B active at inference time
524k
$0.00
5.1
207
Institute of Foundation Models
Beam 1.0
Reflection logoReflection
18
501B
23B active at inference time
1M
$0.23
2.0
281
BasetenCoreWeaveTogether AI
+2
Nemotron 3.5 Super VL
NVIDIA logoNVIDIA
14
120B
12B active at inference time
1M
$0.13
4.7
291
PrimaLabsDeepInfraBitdeer AI
+6