Comparisons of Large Open Source AI Models (>150B)
Open source AI models with over 150B 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.
Openness
Artificial Analysis Openness Index: Score
Intelligence
Artificial Analysis Progress Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
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
Model Size: Total and Active Parameters
Progress Index vs. Active Parameters
Progress Index vs. Total Parameters
Context Window
Context Window
Further details
Weights | Provider Benchmarks | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Kimi K3.1 Pro | 341 | 2.8T 104B active at inference time | 1M | $1.54 | 38.8 | 31 | +15 | |||
DeepSeek V4.1 Flash 1017 (Max) | 324 | 552B 16B active at inference time | 1M | $0.18 | 13.1 | 177 | +23 | |||
GLM-5.3 (Max) | 323 | 753B 40B active at inference time | 1M | $0.90 | 22.2 | 89 | +26 | |||
Ling 3.1 Flash 1019 | 322 | 560B 25B active at inference time | 1M | $0.19 | - | - | ||||
MiMo-V2.6-Pro | 321 | 1T 42B active at inference time | 1M | $0.18 | 37.1 | 54 | ||||
Qwen3.8-Flash-Next | 320 | 180B 6B active at inference time | 256k | $0.0882 | 29.3 | 84 | ||||
DeepSeek V4.1 Flash 1017 (High) | 319 | 552B 16B active at inference time | 1M | $0.18 | 10.3 | 179 | ||||
GLM-5.3-Flash | 319 | 320B 18B active at inference time | 1M | $0.10 | 39.2 | 57 | +23 | |||
Step 5 Preview | 318 | 600B 27B active at inference time | 1M | $0.54 | 14.2 | 133 | ||||
Qwen3.8 2.4T A95B | 318 | 2.4T 95B active at inference time | 262k | $1.18 | - | 41 | +2 | |||
MiniMax-M3.1-Flash | 318 | 428B 23B active at inference time | 1M | $0.10 | 16.3 | 141 | +10 | |||
MiMo-V2.6-Flash | 312 | 309B 15B active at inference time | 1M | $0.058 | 51.2 | 43 |