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 Tencent logoTencent Hy4 are the highest intelligence open source models, followed by DeepSeek logoDeepSeek V4.1 Flash 1017 (max) & Z AI logoGLM-5.3 (max).
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
38.5
31
DatabricksIncoKimi
+15
Tencent Hy4
Tencent logoTencent
35
774B
50.2B active at inference time
1M
$0.45
14.2
91
Tencent
DeepSeek V4.1 Flash 1017 (Max)
DeepSeek logoDeepSeek
33
552B
16B active at inference time
1M
$0.18
14.4
160
BasetenNovitaBaseten
+23
GLM-5.3 (Max)
Z AI logoZ AI
32
753B
40B active at inference time
1M
$0.90
30.2
66
ModalZaiSambaNova
+26
Inkling 2 Small
Thinking Machines logoThinking Machines
31
594B
17B active at inference time
1M
$0.18
23.4
106
DeepInfraNebiusTogether AIThinking Machines
MiMo-V2.6-Pro
Xiaomi logoXiaomi
30
1T
42B active at inference time
1M
$0.18
39.6
51
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
20.5
67
Mistral
Qwen3.8 27B (Xhigh)
Alibaba logoAlibaba
20
27B
256k
$0.47
29.2
63
NebiusDeepInfraCoreWeave
+7
K2 Horizon 375B A23B
Institute of Foundation Models logoInstitute of Foundation Models
18
375B
23B active at inference time
524k
$0.00
3.7
287
Institute of Foundation Models
Beam 1.0
Reflection logoReflection
18
501B
23B active at inference time
1M
$0.23
1.9
294
BasetenTogether AICoreWeave
+2
Nemotron 3.5 Super VL
NVIDIA logoNVIDIA
14
120B
12B active at inference time
1M
$0.11
4.4
311
PrimaLabsDeepInfraBitdeer AI
+6