LIVETracking 971 AI models from 268 providers.
Beta

Flagship AI Models

The best AI model from each provider, ranked by benchmark score. Compare the flagships from OpenAI, Anthropic, Google, Meta, and more.

30
Models
30
Providers
23
Open Source
$0.39
Median $/1M in
#1
Anthropic logo
Claude Mythos Preview
🇺🇸 Anthropic
1.0MN/A/M in
100.014 benchmarks
#2
Alibaba Qwen logo
Qwen3.5 397B A17B
🇨🇳 Alibaba Qwen
Open262K$0.39/M in
96.311 benchmarks
#3
DeepSeek logo
DeepSeek V3.2 Speciale
🇨🇳 DeepSeek
Open164K$0.40/M in
95.29 benchmarks
#ModelAvg$/1M inContext
1Anthropic logoClaude Mythos Preview🇺🇸 Anthropic100.0N/A1.0M
2Alibaba Qwen logoQwen3.5 397B A17B🇨🇳 Alibaba QwenOpen96.3$0.39262K
3DeepSeek logoDeepSeek V3.2 Speciale🇨🇳 DeepSeekOpen95.2$0.40164K
4OpenAI logoGPT-5.4 Pro🇺🇸 OpenAI93.0$30.001.1M
5Google DeepMind logoGemini 3.1 Pro Preview🇺🇸 Google DeepMind90.0$2.001.0M
6stepfun logoStep 3.5 Flash🇨🇳 stepfunOpen89.5$0.10262K
7
HA
Qwen2.5 72B Instruct Abliterated HuiHui AI		87.5N/A0K
8z-ai logoGLM 5.1🇨🇳 z-aiOpen87.0$0.95203K
9xiaomi logoMiMo-V2-Flash🇨🇳 xiaomiOpen81.7$0.09262K
10Microsoft logophi-3-small 7.4B🇺🇸 MicrosoftOpen78.8N/A0K
11
U
Muse Spark Unknown		77.0N/A0K
12Meta logoLlama 3.3 70B Instruct🇺🇸 MetaOpen75.9$0.10131K
13nousresearch logoHermes 3 70B Instruct🇺🇸 nousresearchOpen73.3$0.30131K
14minimax logoMiniMax M2🇨🇳 minimaxOpen72.4$0.26197K
15xAI logoGrok 3 Beta🇺🇸 xAI67.9$3.00131K
16Mistral AI logoMixtral 8x7B Instruct🇫🇷 Mistral AIOpen66.8$0.5433K
17TII logoFalcon 2 11B TIIOpen63.3N/A0K
18moonshotai logoKimi K2 Thinking🇨🇳 moonshotaiOpen61.0$0.60262K
19writer logoPalmyra X5🇺🇸 writer57.0$0.601.0M
20
D
Dolphin 2.9.1 Yi 1.5 34b DPHNOpen		55.9N/A0K
21meituan logoLongCat Flash Chat🇨🇳 meituanOpen53.4$0.20131K
22anthracite-org logoMagnum v4 72B anthracite-orgOpen51.2$3.0016K
23baidu logoERNIE 4.5 21B A3B Thinking🇨🇳 baiduOpen39.8$0.07131K
24tencent logoHunyuan A13B Instruct🇨🇳 tencentOpen29.3$0.14131K
25
L
Vicuna 7b V1.5 LMSYSOpen		19.1N/A0K
26NVIDIA logoNemotron 3 Super🇺🇸 NVIDIAOpen11.6$0.10262K
27eleutherai logoPythia 160m🇺🇸 eleutheraiOpen10.3N/A0K
28
HF
SmolLM2 135M Hugging Face TBOpen		9.4N/A0K
29
D
Distilgpt2 DistilBERTOpen		8.6N/A0K
30
T
TinyLlama 1.1B Chat V1.0 TinyLlamaOpen		3.8N/A0K

The single highest-scoring model from each major provider, ranked by benchmark performance. This view cuts through the noise to show how providers compare at their best.

Best AI Models for Coding

AI models ranked by coding benchmarks. Compare HumanEval+, SWE-bench Verified, Aider Polyglot, and more across all providers.

Best AI Models for Reasoning

AI models ranked by reasoning benchmarks. Compare GPQA Diamond, ARC-AGI, BBH, and other reasoning tests across all providers.

AI Models with 1M+ Context

AI models with 1 million+ token context windows ranked by score. Compare Gemini, Claude, and other long-context models.

Which AI provider has the best flagship model?

Flagship rankings shift frequently as providers release updates. The leaderboard above shows the current top model from each major provider.

How are flagship models selected?

For each provider, we select the single model with the highest average benchmark score. This ensures a fair one-to-one comparison across providers.

Back to all models