Providers
Provider leaderboard surfaces
BenchLM groups canonical model families by creator so you can compare labs, not just single SKUs. Each provider page shows provisional-ranked depth, verified-ranked depth, current releases, and top-performing families.
Showing 38 of 38 providers
Anthropic
Top modelClaude Mythos Preview
Avg. top 3 score95
Provisional-ranked12
Verified-ranked4
Current releases4
OpenAI
Top modelGPT-5.4
Avg. top 3 score88.3
Provisional-ranked14
Verified-ranked1
Current releases7
Top modelGemini 3.1 Pro
Avg. top 3 score81.3
Provisional-ranked10
Verified-ranked0
Current releases5
Z.AI
Top modelGLM-5.1
Avg. top 3 score77.7
Provisional-ranked5
Verified-ranked1
Current releases1
xAI
Top modelGrok 4.1
Avg. top 3 score76.3
Provisional-ranked6
Verified-ranked0
Current releases2
Alibaba
Top modelQwen3.6 Plus
Avg. top 3 score70.3
Provisional-ranked9
Verified-ranked6
Current releases8
MiniMax
Top modelMiniMax M2.7
Avg. top 3 score65
Provisional-ranked1
Verified-ranked0
Current releases1
Xiaomi
Top modelMiMo-V2-Flash
Avg. top 3 score63
Provisional-ranked1
Verified-ranked0
Current releases3
DeepSeek
Top modelDeepSeek V3.2
Avg. top 3 score55.7
Provisional-ranked7
Verified-ranked0
Current releases1
Moonshot AI
Top modelKimi K2.5
Avg. top 3 score45.3
Provisional-ranked3
Verified-ranked1
Current releases1
Sarvam
Top modelSarvam 105B
Avg. top 3 score41
Provisional-ranked1
Verified-ranked0
Current releases2
NVIDIA
Top modelNemotron 3 Ultra 500B
Avg. top 3 score40.3
Provisional-ranked5
Verified-ranked0
Current releases5
Mistral
Top modelMistral Large 3
Avg. top 3 score39
Provisional-ranked5
Verified-ranked0
Current releases7
Databricks
Top modelDBRX Instruct
Avg. top 3 score33
Provisional-ranked1
Verified-ranked0
Current releases0
Meta
Top modelLlama 3.1 405B
Avg. top 3 score31.7
Provisional-ranked5
Verified-ranked0
Current releases4
Microsoft
Top modelPhi-4
Avg. top 3 score29
Provisional-ranked1
Verified-ranked0
Current releases0
Z
Top modelZ-1
Avg. top 3 score25
Provisional-ranked1
Verified-ranked0
Current releases0
Amazon
Top modelNova Pro
Avg. top 3 score11
Provisional-ranked1
Verified-ranked0
Current releases0
H Company
Top modelHolo3-122B-A10B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases1
Cursor
Top modelComposer 2
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases1
LG AI Research
Top modelExaone 4.0 32B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Prism ML
Top modelTernary Bonsai 8B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases2
StepFun
Top modelStep 3.5 Flash
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases1
Inception
Top modelMercury 2
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases1
Arcee AI
Top modelTrinity-Large-Thinking
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases1
LiquidAI
Top modelLFM2.5-350M
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases4
ByteDance
Top modelSeed 1.6
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases1
IBM
Top modelGranite-4.0-H-1B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases2
Aion Labs
Top modelAion-2.0
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Upstage
Top modelSolar Pro 2
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
SK Telecom
Top modelA.X series
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Community
Top modelDNA 1.0 8B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Naver Cloud
Top modelHyperClova X Think 32B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Kakao
Top modelKanana Flag
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
LightOn
Top modelOriOn-Qwen-32B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Aleph Alpha
Top modelPharia-1-LLM-7B-control
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
Academic
Top modelThunder-LLM 8B
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0
NC AI
Top modelVarco
Avg. top 3 scoreN/A
Provisional-ranked0
Verified-ranked0
Current releases0