Open weights
Use this open model leaderboard to compare the current open-weight ranking from aggregated benchmark evidence, capability, context, licenses, pricing and runtime.
Data as of 2026-09-08
This leaderboard ranks each model using its latest scored open-weight version and eligible benchmark evidence.
Rank | Model | LLMBoard Score | License | Parameters | Context | Official input / 1M | Output speed |
|---|
| Rank01 | ModelMA | LLMBoard Score89.45 | LicenseOpen | Parameters2.8T | Context1M | Official input / 1M$3 | Output speedN/A |
| Rank02 | ModelZA | LLMBoard Score88.97 | LicenseOpen | Parameters753B | Context1M | Official input / 1M$1.4 | Output speed472.69 tok/s |
| Rank03 | ModelAC | LLMBoard Score86.93 | LicenseOpen | Parameters2.4T | Context1M | Official input / 1M$2 | Output speed60.87 tok/s |
| Rank04 | ModelDE | LLMBoard Score86.78 | LicenseOpen | Parameters1.6T | Context1M | Official input / 1MN/A | Output speed45.48 tok/s |
| Rank05 | ModelZA | LLMBoard Score84.28 | LicenseOpen | Parameters320B | Context1M | Official input / 1M$0.075 | Output speed74.28 tok/s |
| Rank06 | ModelTE | LLMBoard Score83.71 | LicenseOpen | Parameters770B | ContextN/A | Official input / 1MN/A | Output speedN/A |
| Rank07 | ModelAC | LLMBoard Score81.44 | LicenseOpen | Parameters125B | ContextN/A | Official input / 1MN/A | Output speedN/A |
| Rank08 | ModelAC | LLMBoard Score81.35 | LicenseOpen | Parameters125B | Context1M | Official input / 1M$0.15 | Output speedN/A |
| Rank09 | ModelZA | LLMBoard Score77.02 | LicenseOpen | Parameters753B | Context1M | Official input / 1M$1.4 | Output speed3.96 tok/s |
| Rank10 | ModelAC | LLMBoard Score74.94 | LicenseOpen | Parameters27.8B | Context262.1K | Official input / 1MN/A | Output speedN/A |
| Rank11 | ModelMA | LLMBoard Score73.54 | LicenseOpen | Parameters1T | Context262.1K | Official input / 1M$0.95 | Output speed1.24 tok/s |
| Rank12 | ModelTE | LLMBoard Score71.35 | LicenseOpen | Parameters295B | ContextN/A | Official input / 1MN/A | Output speedN/A |
| Rank13 | ModelMI | LLMBoard Score69.20 | LicenseOpen | Parameters428B | Context1M | Official input / 1M$0.30 | Output speed6.61 tok/s |
| Rank14 | ModelPO | LLMBoard Score67.97 | LicenseOpen | Parameters118B | Context1M | Official input / 1MN/A | Output speedN/A |
| Rank15 | ModelZA | LLMBoard Score67.64 | LicenseOpen | Parameters754B | Context200K | Official input / 1M$1.4 | Output speedN/A |
| Rank16 | ModelMA | LLMBoard Score65.57 | LicenseOpen | Parameters1T | Context262.1K | Official input / 1MN/A | Output speedN/A |
| Rank17 | ModelMA | LLMBoard Score65.53 | LicenseOpen | Parameters1T | Context262.1K | Official input / 1M$0.95 | Output speedN/A |
| Rank18 | ModelAC | LLMBoard Score64.55 | LicenseOpen | Parameters397B | Context262.1K | Official input / 1M$0.60 | Output speedN/A |
| Rank19 | ModelTM | LLMBoard Score63.90 | LicenseOpen | Parameters276B | Context256K | Official input / 1MN/A | Output speedN/A |
| Rank20 | ModelNV | LLMBoard Score61.30 | LicenseOpen | Parameters550B | ContextN/A | Official input / 1M$0.50 | Output speedN/A |
| Rank21 | ModelXI | LLMBoard Score60.00 | LicenseOpen | Parameters310.8B | Context1M | Official input / 1M$0.14 | Output speed5.39 tok/s |
| Rank22 | ModelMA | LLMBoard Score59.99 | LicenseOpen | Parameters1T | Context262.1K | Official input / 1MN/A | Output speedN/A |
| Rank23 | ModelME | LLMBoard Score59.49 | LicenseOpen | Parameters560B | Context128K | Official input / 1MN/A | Output speedN/A |
| Rank24 | ModelST | LLMBoard Score59.42 | LicenseOpen | Parameters196B | Context65.5K | Official input / 1M$0.10 | Output speed21.16 tok/s |
| Rank25 | ModelAC | LLMBoard Score58.93 | LicenseOpen | Parameters27.8B | Context262.1K | Official input / 1M$0.60 | Output speedN/A |
| Rank26 | ModelZA | LLMBoard Score58.55 | LicenseOpen | Parameters358B | Context204.8K | Official input / 1M$0.60 | Output speedN/A |
| Rank27 | ModelGO | LLMBoard Score58.54 | LicenseOpen | Parameters30.7B | Context262.1K | Official input / 1MN/A | Output speed22.86 tok/s |
| Rank28 | ModelAC | LLMBoard Score58.22 | LicenseOpen | Parameters122B | Context262.1K | Official input / 1M$0.40 | Output speedN/A |
| Rank29 | ModelME | LLMBoard Score57.39 | LicenseOpen | Parameters29.6B | ContextN/A | Official input / 1MN/A | Output speedN/A |
| Rank30 | ModelAC | LLMBoard Score56.05 | LicenseOpen | Parameters27B | Context262.1K | Official input / 1M$0.30 | Output speedN/A |
Open-weight status belongs to the scored model version. License terms still need to be checked on the model detail page.
Key leaders and coverage signals from the current open-weight ranking.
Each capability benchmark remains a separate score alongside the overall leaderboard.
Vendor, license and model-size patterns across models in the current ranking.
Only positive official vendor PAYG prices are included. Price and benchmark-backed capability remain separate leaderboard signals.
The current top five entries in the open model leaderboard, summarized with benchmark capability, official price, output speed and deployment-relevant evidence.
Common questions about this open model leaderboard, benchmark coverage and ranking.
Kimi K3 currently leads the open-model leaderboard ranking.
The current leaders are Kimi K3 (89.45 LLMBoard score), GLM 5.3 (88.97 LLMBoard score), and Qwen3.8 Max (86.93 LLMBoard score).
Min istral 3 has the lowest listed official input price at $0.04 per 1M tokens.
The fastest matched records are Llama 3.3 70B (2,220.00 tok/s via Cerebras), Llama 3.1 8B (2,047.00 tok/s via Cerebras), and Min istral 3 (1,222.00 tok/s via Mistral AI).
Llama 4 Scout has the largest listed context window at 10M tokens.
The scored model version is marked as having publicly available weights. That flag does not by itself determine whether the license permits every commercial or derivative use.
This page currently ranks 166 unique open-weight models.
Each row names the latest open-weight version with a current LLMBoard score derived from eligible benchmark evidence.
Ranking basisThis open-weight use AI model leaderboard uses the current LLMBoard capability score among versions marked as open weight. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
Kimi K3 is the highest-ranked open-weight model at 89.45. The best open LLM also depends on license terms, hardware needs, context, price and available runtime records.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.