AI Providers

51 labs and providers tracked across five independent leaderboards.

Anthropic
Claude Mythos Preview97.4
75 models⌀ 52.9
OpenAI
GPT-6 Astra (xhigh)87.0
123 models⌀ 47.42 open weights
Moonshot AI
Kimi K383.3
16 models⌀ 52.13 open weights
Alibaba
Qwen3.8 Max79.8
95 models⌀ 38.058 open weights
Google
Gemini 3.1 Pro Preview74.0
68 models⌀ 43.314 open weights
xAI
Grok 4.20 Beta174.0
36 models⌀ 52.4
DeepSeek
Deepseek V4 Pro High Preview73.0
36 models⌀ 47.221 open weights
Z.ai
Glm 5.2 Max73.0
24 models⌀ 52.312 open weights
Baidu
Ernie 5.0 Preview 120372.0
5 models⌀ 54.6
LongCat
Longcat Flash Chat 2602 Exp72.0
3 models⌀ 69.01 open weights
Amazon
Amazon Nova Experimental Chat 26 02 1071.0
25 models⌀ 35.5
NVIDIA
Nvidia Nemotron 3 Ultra 550b A55b Nvfp471.0
17 models⌀ 26.31 open weights
Tencent
Hunyuan Hy3 Preview71.0
13 models⌀ 59.4
MiniMax
Minimax M2.570.0
9 models⌀ 41.24 open weights
Mistral
Mistral Medium 250870.0
35 models⌀ 30.416 open weights
StepFun
Step 3.5 Flash70.0
7 models⌀ 55.7
Meta
Muse Spark 1.169.9
42 models⌀ 39.117 open weights
Cohere
Command A 03 202568.0
12 models⌀ 39.9
AI2
Olmo 3.1 32b Instruct67.0
7 models⌀ 54.51 open weights
Ling
Ling Flash 2.067.0
7 models⌀ 36.1
AI9Stars
G9v3-39A5B65.0
2 models⌀ 65.02 open weights
IBM
Granite 4.1 8b65.0
10 models⌀ 45.75 open weights
Inception
Mercury65.0
3 models⌀ 47.3
Kwai
KAT-Coder-Pro V265.0
1 model⌀ 65.0
Liquid AI
LFM2.5-2.6B65.0
3 models⌀ 65.03 open weights
Multiverse
HyperNova 60B65.0
1 model⌀ 65.01 open weights
Zhipu AI
GLM-5.365.0
2 models⌀ 62.5
Muse
Muse Spark 1.363.5
2 models⌀ 31.8
Microsoft
Phi 3 Medium 4k Instruct60.0
10 models⌀ 46.61 open weights
Xiaomi
MiMo V2.6 Pro52.5
5 models⌀ 39.85 open weights
Sarvam AI
Sarvam 105B50.0
3 models⌀ 49.73 open weights
Agnes
Agnes 3.0 Flash48.2
3 models⌀ 43.5
Nex AGI
Nex N2 Pro44.4
1 model⌀ 44.4
Thinking Machines
Inkling Small41.7
2 models⌀ 36.7
Upstage
Solar Pro441.6
4 models⌀ 17.7
ByteDance
Seed 2.0 Pro40.0
2 models⌀ 29.3
WeRide
Ring 2 6 1t31.3
1 model⌀ 31.3
K2
K2 Think V222.0
1 model⌀ 22.0
ServiceNow
Apriel V1 5 15b Thinker21.6
2 models⌀ 21.2
North
North Mini Code20.2
1 model⌀ 20.2
Trinity
Trinity Large Thinking18.4
1 model⌀ 18.4
Celeris
Celeris 112.4
1 model⌀ 12.4
Reka
Reka Flash6.0
2 models⌀ 4.9
AI21 Labs
Jamba 1 5 Large4.8
2 models⌀ 3.6
Swiss AI
Apertus 70b Instruct2.0
2 models⌀ 1.5
Async
Async Flash V1 50.0
3 models⌀ 0.0
Cogito
Cogito V2 1 Reasoning0.0
1 model⌀ 0.0
Independent
Apodex 1.10.0
1 model⌀ 0.01 open weights
Ocat
Ocateve 20.0
1 model⌀ 0.0
Open Source
Quasar 438B0.0
1 model⌀ 0.01 open weights
TII
Falcon 20.0
1 model⌀ 0.01 open weights
0 / 4
Compare Now →