LLM Leaderboard - Comparison of over 100 AI models from OpenAI, Google, DeepSeek & others
Comparison and ranking the performance of over 100 AI models (LLMs) across key metrics including intelligence, price, performance and speed (output speed - tokens per second & latency - TTFT), context window & others. For more details including relating to our methodology, see our FAQs.
Intelligence
Gemini 3.1 Pro Preview and GPT-5.4 (xhigh) are the highest intelligence models, followed by GPT-5.3 Codex (xhigh) and Claude Opus 4.6 (max).
Output Speed
Mercury 2 and Granite 4.0 H Small are the fastest models, followed by Qwen3.5 0.8B and Qwen3.5 0.8B.
Latency
Qwen3.5 0.8B and Qwen3.5 0.8B are the lowest latency models, followed by Qwen3.5 2B and Qwen3.5 2B.
Price
Qwen3.5 0.8B and Qwen3.5 0.8B are the cheapest models, followed by Gemma 3n E4B and Qwen3.5 2B.
Context Window
Llama 4 Scout and Grok 4.20 Beta 0309 support the largest context windows, followed by Grok 4.20 Beta 0309 and Gemini 1.5 Pro (May).
Further Analysis | ||||||||
|---|---|---|---|---|---|---|---|---|
Gemini 3.1 Pro Preview | 1M | Google | 57 | $4.50 | 109 | 34.38 | 38.96 | |
GPT-5.4 (xhigh) | 1.05M | OpenAI | 57 | $5.63 | 80 | 127.93 | 134.19 | |
GPT-5.3 Codex (xhigh) | 400k | OpenAI | 54 | $4.81 | 73 | 104.07 | 110.96 | |
Claude Opus 4.6 (max) | 1M | Anthropic | 53 | $10.00 | 43 | 19.60 | 31.26 | |
Claude Sonnet 4.6 (max) | 1M | Anthropic | 52 | $6.00 | 68 | 89.80 | 97.11 | |
GPT-5.2 (xhigh) | 400k | OpenAI | 51 | $4.81 | 70 | 177.74 | 184.87 | |
GLM-5 | 200k |  Z AI | 50 | $1.55 | 68 | 1.62 | 54.41 | |
Claude Opus 4.5 | 200k | Anthropic | 50 | $10.00 | 50 | 17.18 | 27.09 | |
MiniMax-M2.7 | 205k |  MiniMax | 50 | $0.53 | 45 | 2.37 | 68.90 | |
MiMo-V2-Pro | 1M |  Xiaomi | 49 | $1.50 | -- | -- | -- | |
GPT-5.2 Codex (xhigh) | 400k | OpenAI | 49 | $4.81 | 130 | 79.43 | 83.27 | |
Grok 4.20 Beta 0309 | 2M | xAI | 48 | $3.00 | 248 | 10.93 | 12.95 | |
Gemini 3 Pro Preview (high) | 1M | Google | 48 | $4.50 | 121 | 43.92 | 48.06 | |
GPT-5.4 mini (xhigh) | 400k | OpenAI | 48 | $1.69 | 204 | 9.48 | 11.93 | |
GPT-5.1 (high) | 400k | OpenAI | 48 | $3.44 | 83 | 63.66 | 69.66 | |
Kimi K2.5 | 256k |  Kimi | 47 | $1.20 | 43 | 2.45 | 60.46 | |
GLM-5-Turbo | 200k | Z AI | 47 | -- | -- | -- | -- | |
GPT-5.2 (medium) | 400k | OpenAI | 47 | $4.81 | -- | -- | -- | |
Claude Opus 4.6 | 1M | Anthropic | 46 | $10.00 | 41 | 1.91 | 14.22 | |
Gemini 3 Flash | 1M | Google | 46 | $1.13 | 164 | 7.89 | 10.93 | |
Qwen3.5 397B A17B | 262k | Alibaba | 45 | $1.35 | 88 | 2.44 | 44.56 | |
GPT-5 (high) | 400k | OpenAI | 45 | $3.44 | 101 | 80.61 | 85.54 | |
GPT-5 Codex (high) | 400k | OpenAI | 45 | $3.44 | 193 | 14.18 | 16.78 | |
GPT-5.4 nano (xhigh) | 400k | OpenAI | 44 | $0.46 | 192 | 3.72 | 6.32 | |
Claude Sonnet 4.6 | 1M | Anthropic | 44 | $6.00 | 43 | 1.78 | 13.38 | |
MiMo-V2-Omni | 256k | Xiaomi | 43 | -- | -- | -- | -- | |
GPT-5.1 Codex (high) | 400k | OpenAI | 43 | $3.44 | 134 | 11.45 | 15.17 | |
Claude Opus 4.5 | 200k | Anthropic | 43 | $10.00 | 46 | 1.37 | 12.18 | |
Claude 4.5 Sonnet | 1M | Anthropic | 43 | $6.00 | 45 | 15.12 | 26.17 | |
Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 1M | Anthropic | 43 | $6.00 | 43 | 1.91 | 13.56 | |
GLM-4.7 | 200k | Z AI | 42 | $1.00 | 73 | 1.13 | 35.20 | |
Qwen3.5 27B | 262k | Alibaba | 42 | $0.82 | 84 | 5.65 | 35.55 | |
GPT-5 (medium) | 400k | OpenAI | 42 | $3.44 | 89 | 34.69 | 40.30 | |
Claude 4.1 Opus | 200k | Anthropic | 42* | $30.00 | 38 | 13.14 | 26.21 | |
MiniMax-M2.5 | 205k | MiniMax | 42 | $0.53 | 52 | 2.05 | 50.05 | |
DeepSeek V3.2 | 128k |  DeepSeek | 42 | $0.32 | 34 | 1.79 | 74.72 | |
Qwen3.5 122B A10B | 262k | Alibaba | 42 | $1.10 | 134 | 2.32 | 21.03 | |
Grok 4 | 256k | xAI | 42 | $6.00 | 53 | 15.33 | 24.81 | |
MiMo-V2-Flash (Feb 2026) | 256k | Xiaomi | 41 | $0.15 | 118 | 2.82 | 23.97 | |
Gemini 3 Pro Preview (low) | 1M | Google | 41 | $4.50 | -- | -- | -- | |
GPT-5 mini (high) | 400k | OpenAI | 41 | $0.69 | 84 | 100.47 | 106.39 | |
Kimi K2 Thinking | 256k | Kimi | 41 | $1.07 | 96 | 1.37 | 27.55 | |
o3-pro | 200k | OpenAI | 41* | $35.00 | 22 | 121.74 | 144.47 | |
GLM-5 | 200k | Z AI | 41 | $1.55 | 59 | 1.67 | 10.10 | |
Qwen3.5 397B A17B | 262k | Alibaba | 40 | $1.35 | 84 | 2.48 | 8.46 | |
Qwen3 Max Thinking | 256k | Alibaba | 40 | $2.40 | 37 | 3.86 | 72.01 | |
MiniMax-M2.1 | 205k | MiniMax | 39 | $0.53 | 56 | 2.37 | 47.13 | |
MiMo-V2-Flash | 256k | Xiaomi | 39 | $0.15 | 117 | 2.33 | 23.76 | |
GPT-5 (low) | 400k | OpenAI | 39 | $3.44 | 80 | 9.63 | 15.87 | |
Claude 4 Opus | 200k | Anthropic | 39* | $30.00 | 37 | 14.75 | 28.44 | |
GPT-5 mini (medium) | 400k | OpenAI | 39 | $0.69 | 78 | 19.63 | 26.00 | |
Claude 4 Sonnet | 1M | Anthropic | 39 | $6.00 | 48 | 16.61 | 27.12 | |
GPT-5.1 Codex mini (high) | 400k | OpenAI | 39 | $0.69 | 176 | 10.22 | 13.06 | |
Grok 4.1 Fast | 2M | xAI | 39 | $0.28 | 139 | 9.87 | 13.47 | |
o3 | 200k | OpenAI | 38 | $3.50 | 101 | 7.45 | 12.42 | |
GPT-5.4 nano | 400k | OpenAI | 38 | $0.46 | 198 | 3.25 | 5.78 | |
Step 3.5 Flash | 256k |  StepFun | 38 | $0.15 | 87 | 4.09 | 32.99 | |
GPT-5.4 mini (medium) | 400k | OpenAI | 38 | $1.69 | 187 | 5.54 | 8.21 | |
Kimi K2.5 | 256k | Kimi | 37 | $1.20 | 43 | 3.72 | 15.26 | |
Qwen3.5 27B | 262k | Alibaba | 37 | $0.82 | 87 | 5.67 | 11.43 | |
Claude 4.5 Sonnet | 1M | Anthropic | 37 | $6.00 | 42 | 1.45 | 13.36 | |
Qwen3.5 35B A3B | 262k | Alibaba | 37 | $0.69 | 174 | 2.06 | 16.41 | |
Claude 4.5 Haiku | 200k | Anthropic | 37 | $2.00 | 109 | 18.99 | 23.56 | |
MiniMax-M2 | 205k | MiniMax | 36 | $0.53 | 50 | 1.97 | 52.03 | |
Claude 4.1 Opus | 200k | Anthropic | 36* | $30.00 | 31 | 1.59 | 17.54 | |
NVIDIA Nemotron 3 Super | 1M |  NVIDIA | 36 | $0.41 | 388 | 0.71 | 7.16 | |
Qwen3.5 122B A10B | 262k | Alibaba | 36 | $1.10 | 120 | 2.30 | 6.46 | |
Nova 2.0 Pro Preview (medium) | 256k |  Amazon | 36 | $3.44 | 116 | 15.79 | 37.37 | |
GPT-5.4 | 1.05M | OpenAI | 35 | $5.63 | 68 | 0.81 | 8.14 | |
Grok 4 Fast | 2M | xAI | 35 | $0.28 | 150 | 5.33 | 8.65 | |
Gemini 3 Flash | 1M | Google | 35 | $1.13 | 171 | 1.65 | 4.58 | |
Claude 3.7 Sonnet | 200k | Anthropic | 35 | $6.00 | -- | -- | -- | |
Gemini 2.5 Pro | 1M | Google | 35 | $3.44 | 128 | 26.62 | 30.54 | |
GLM-4.7 | 200k | Z AI | 34 | $0.94 | 74 | 1.15 | 7.88 | |
DeepSeek V3.1 Terminus | 128k | DeepSeek | 34 | $0.80 | -- | -- | -- | |
GPT-5.2 | 400k | OpenAI | 34 | $4.81 | 71 | 0.78 | 7.85 | |
Gemini 3.1 Flash-Lite Preview | 1M | Google | 34 | $0.56 | 225 | 7.68 | 9.90 | |
Doubao Seed Code | 256k |  ByteDance Seed | 34 | -- | -- | -- | -- | |
gpt-oss-120B (high) | 131k | OpenAI | 33 | $0.26 | 242 | 0.79 | 11.10 | |
o4-mini (high) | 200k | OpenAI | 33 | $1.93 | 122 | 36.76 | 40.87 | |
Claude 4 Opus | 200k | Anthropic | 33* | $30.00 | 32 | 1.63 | 17.09 | |
Claude 4 Sonnet | 1M | Anthropic | 33 | $6.00 | 43 | 1.31 | 12.86 | |
DeepSeek V3.2 Exp | 128k | DeepSeek | 33 | $0.32 | 35 | 1.72 | 72.24 | |
Mercury 2 | 128k | Inception | 33 | $0.38 | 835 | 4.23 | 4.82 | |
GLM-4.6 | 200k | Z AI | 33 | $0.98 | 71 | 1.49 | 36.60 | |
Qwen3 Max Thinking (Preview) | 262k | Alibaba | 32 | $2.40 | 45 | 4.02 | 59.35 | |
Qwen3.5 9B | 262k | Alibaba | 32 | $0.10 | 205 | 1.04 | 13.23 | |
K-EXAONE | 256k |  LG AI Research | 32 | -- | -- | -- | -- | |
DeepSeek V3.2 | 128k | DeepSeek | 32 | $0.32 | 34 | 1.74 | 16.42 | |
Grok 3 mini Reasoning (high) | 1M | xAI | 32 | $0.35 | 190 | 0.56 | 13.70 | |
Nova 2.0 Pro Preview (low) | 256k | Amazon | 32 | $3.44 | 118 | 12.14 | 33.30 | |
Qwen3 Max | 262k | Alibaba | 31 | $2.40 | 63 | 2.70 | 10.69 | |
Gemini 2.5 Flash (Sep) | 1M | Google | 31 | -- | -- | -- | -- | |
Claude 4.5 Haiku | 200k | Anthropic | 31 | $2.00 | 91 | 0.65 | 6.12 | |
Kimi K2 0905 | 256k | Kimi | 31 | $1.14 | 35 | 1.19 | 15.39 | |
Claude 3.7 Sonnet | 200k | Anthropic | 31 | $6.00 | -- | -- | -- | |
o1 | 200k | OpenAI | 31 | $26.25 | 89 | 37.76 | 43.41 | |
Qwen3.5 35B A3B | 262k | Alibaba | 31 | $0.69 | 153 | 2.00 | 5.27 | |
MiMo-V2-Flash | 256k | Xiaomi | 30 | $0.15 | 117 | 2.13 | 6.38 | |
Gemini 2.5 Pro (Mar) | 1M | Google | 30* | -- | -- | -- | -- | |
GLM-4.6 | 200k | Z AI | 30 | $1.00 | 27 | 1.79 | 20.02 | |
GLM-4.7-Flash | 200k | Z AI | 30 | $0.15 | 74 | 0.96 | 34.71 | |
Nova 2.0 Lite (medium) | 1M | Amazon | 30 | $0.85 | 158 | 15.02 | 30.80 | |
Grok 4.20 Beta 0309 | 2M | xAI | 30 | $3.00 | 205 | 0.54 | 2.98 | |
Gemini 2.5 Pro (May) | 1M | Google | 30* | $3.44 | -- | -- | -- | |
Qwen3 235B A22B 2507 | 256k | Alibaba | 30 | $2.63 | 41 | 2.83 | 64.39 | |
DeepSeek V3.2 Speciale | 128k | DeepSeek | 29 | -- | -- | -- | -- | |
ERNIE 5.0 Thinking Preview | 128k |  Baidu | 29 | -- | -- | -- | -- | |
Grok Code Fast 1 | 256k | xAI | 29 | $0.53 | 184 | 2.85 | 5.56 | |
DeepSeek V3.1 Terminus | 128k | DeepSeek | 29 | $0.63 | -- | -- | -- | |
DeepSeek V3.2 Exp | 128k | DeepSeek | 28 | $0.32 | 34 | 1.74 | 16.25 | |
Qwen3 Coder Next | 256k | Alibaba | 28 | $0.60 | 148 | 1.60 | 4.97 | |
DeepSeek V3.1 | 128k | DeepSeek | 28 | $0.84 | -- | -- | -- | |
Nova 2.0 Omni (medium) | 1M | Amazon | 28 | $0.85 | -- | -- | -- | |
Nemotron Cascade 2 30B A3B | 262k | NVIDIA | 28 | -- | -- | -- | -- | |
DeepSeek V3.1 | 128k | DeepSeek | 28 | $0.88 | -- | -- | -- | |
Qwen3 VL 235B A22B | 262k | Alibaba | 28 | $2.63 | 50 | 3.09 | 52.85 | |
GPT-5.1 | 400k | OpenAI | 27 | $3.44 | 77 | 1.11 | 7.62 | |
Qwen3.5 9B | 262k | Alibaba | 27 | $0.08 | 188 | 1.04 | 3.70 | |
Mistral Small 4 | 256k |  Mistral | 27 | $0.26 | 149 | 0.69 | 17.52 | |
Magistral Medium 1.2 | 128k | Mistral | 27 | $2.75 | 95 | 1.65 | 27.92 | |
Qwen3.5 4B | 262k | Alibaba | 27 | $0.06 | 254 | 0.49 | 10.33 | |
DeepSeek R1 0528 | 128k | DeepSeek | 27 | $2.36 | -- | -- | -- | |
Gemini 2.5 Flash | 1M | Google | 27 | $0.85 | 230 | 15.24 | 17.42 | |
GPT-5 nano (high) | 400k | OpenAI | 27 | $0.14 | 127 | 130.56 | 134.49 | |
Qwen3 Next 80B A3B | 262k | Alibaba | 27 | $1.88 | 146 | 2.06 | 19.19 | |
GLM-4.5 | 128k | Z AI | 26 | $0.84 | 48 | 2.84 | 54.62 | |
Kimi K2 | 128k | Kimi | 26 | $1.00 | 36 | 1.66 | 15.72 | |
GPT-4.1 | 1M | OpenAI | 26 | $3.50 | 106 | 1.04 | 5.76 | |
Qwen3 Max (Preview) | 262k | Alibaba | 26 | $2.40 | 42 | 4.16 | 16.15 | |
GPT-5 nano (medium) | 400k | OpenAI | 26 | $0.14 | 134 | 53.46 | 57.18 | |
o3-mini | 200k | OpenAI | 26* | $1.93 | 132 | 8.91 | 12.69 | |
o1-pro | 200k | OpenAI | 26* | $262.50 | -- | -- | -- | |
Gemini 2.5 Flash (Sep) | 1M | Google | 26 | -- | -- | -- | -- | |
o3-mini (high) | 200k | OpenAI | 25 | $1.93 | 137 | 30.15 | 33.79 | |
Grok 3 | 1M | xAI | 25 | $6.00 | 65 | 1.35 | 8.99 | |
Seed-OSS-36B-Instruct | 512k | ByteDance Seed | 25 | $0.30 | 36 | 3.12 | 71.70 | |
Qwen3 235B 2507 | 256k | Alibaba | 25 | $1.23 | 53 | 2.41 | 11.83 | |
Qwen3 Coder 480B | 262k | Alibaba | 25 | $3.00 | 55 | 3.03 | 12.07 | |
Qwen3 VL 32B | 256k | Alibaba | 25 | $2.63 | 89 | 2.61 | 30.65 | |
Sonar Reasoning Pro | 127k |  Perplexity | 25* | -- | -- | -- | -- | |
Nova 2.0 Lite (low) | 1M | Amazon | 25 | $0.85 | 186 | 7.84 | 21.25 | |
gpt-oss-120B (low) | 131k | OpenAI | 24 | $0.26 | 243 | 0.84 | 11.12 | |
gpt-oss-20B (high) | 131k | OpenAI | 24 | $0.09 | 301 | 0.65 | 8.94 | |
MiniMax M1 80k | 1M | MiniMax | 24 | $0.96 | -- | -- | -- | |
GPT-5.4 nano | 400k | OpenAI | 24 | $0.46 | 185 | 0.60 | 3.30 | |
Gemini 2.5 Flash | 1M | Google | 24* | -- | -- | -- | -- | |
NVIDIA Nemotron 3 Nano | 1M | NVIDIA | 24 | $0.10 | 150 | 2.64 | 19.28 | |
LongCat Flash Lite | 256k |  LongCat | 24 | $0.00 | 102 | 6.03 | 10.93 | |
GPT-5 (minimal) | 400k | OpenAI | 24 | $3.44 | 88 | 1.31 | 6.98 | |
o1-preview | 128k | OpenAI | 24* | $28.88 | -- | -- | -- | |
Grok 4.1 Fast | 2M | xAI | 24 | $0.28 | 125 | 0.51 | 4.52 | |
GLM-4.6V | 128k | Z AI | 23 | $0.45 | 24 | 1.95 | 104.03 | |
K-EXAONE | 256k | LG AI Research | 23 | -- | -- | -- | -- | |
GPT-5.4 mini | 400k | OpenAI | 23 | $1.69 | 190 | 0.56 | 3.19 | |
Nova 2.0 Omni (low) | 1M | Amazon | 23 | $0.85 | -- | -- | -- | |
GLM-4.5-Air | 128k | Z AI | 23 | $0.42 | 94 | 1.28 | 27.77 | |
Grok 4 Fast | 2M | xAI | 23 | $0.28 | 124 | 0.53 | 4.55 | |
Nova 2.0 Pro Preview | 256k | Amazon | 23 | $3.44 | 118 | 0.79 | 5.03 | |
Mi:dm K 2.5 Pro | 128k |  Korea Telecom | 23 | -- | -- | -- | -- | |
GPT-4.1 mini | 1M | OpenAI | 23 | $0.70 | 70 | 0.80 | 7.94 | |
Mistral Large 3 | 256k | Mistral | 23 | $0.75 | 45 | 1.20 | 12.30 | |
Ring-1T | 128k |  InclusionAI | 23 | -- | -- | -- | -- | |
Qwen3.5 4B | 262k | Alibaba | 23 | $0.06 | 232 | 0.48 | 2.63 | |
Qwen3 30B A3B 2507 | 262k | Alibaba | 22 | $0.75 | 146 | 2.42 | 19.56 | |
DeepSeek V3 0324 | 128k | DeepSeek | 22 | $1.25 | -- | -- | -- | |
INTELLECT-3 | 131k |  Prime Intellect | 22 | -- | -- | -- | -- | |
GLM-4.7-Flash | 200k | Z AI | 22 | $0.15 | 75 | 1.49 | 8.15 | |
Devstral 2 | 256k | Mistral | 22 | $0.00 | 75 | 0.85 | 7.48 | |
GPT-5 (ChatGPT) | 128k | OpenAI | 22* | $3.44 | 138 | 0.87 | 4.48 | |
Solar Open 100B | 128k |  Upstage | 22 | -- | -- | -- | -- | |
Gemini 2.5 Flash-Lite (Sep) | 1M | Google | 22 | $0.17 | 319 | 9.68 | 11.25 | |
Grok 3 Reasoning Beta | 1M | xAI | 22* | -- | -- | -- | -- | |
Mistral Medium 3.1 | 128k | Mistral | 21 | $0.80 | 52 | 1.38 | 11.05 | |
MiniMax M1 40k | 1M | MiniMax | 21* | -- | -- | -- | -- | |
gpt-oss-20B (low) | 131k | OpenAI | 21 | $0.09 | 300 | 0.70 | 9.03 | |
Qwen3 VL 235B A22B | 262k | Alibaba | 21 | $1.23 | 56 | 2.67 | 11.54 | |
GPT-5 mini (minimal) | 400k | OpenAI | 21 | $0.69 | 74 | 1.46 | 8.26 | |
Gemini 2.5 Flash | 1M | Google | 21 | $0.85 | 219 | 0.53 | 2.81 | |
o1-mini | 128k | OpenAI | 20* | -- | -- | -- | -- | |
Qwen3 Next 80B A3B | 262k | Alibaba | 20 | $0.88 | 154 | 2.12 | 5.37 | |
Qwen3 Coder 30B A3B | 262k | Alibaba | 20 | $0.90 | 26 | 2.61 | 22.19 | |
GPT-4.5 (Preview) | 128k | OpenAI | 20* | -- | -- | -- | -- | |
Qwen3 235B | 32.8k | Alibaba | 20 | $2.63 | 52 | 2.77 | 51.20 | |
QwQ-32B | 131k | Alibaba | 20* | $0.74 | -- | -- | -- | |
Qwen3 VL 30B A3B | 256k | Alibaba | 20 | $0.75 | 110 | 2.14 | 24.86 | |
Gemini 2.0 Flash Thinking exp. (Jan) | 1M | Google | 20* | -- | -- | -- | -- | |
Devstral Small 2 | 256k | Mistral | 19 | $0.00 | 96 | 0.83 | 6.04 | |
Gemini 2.5 Flash-Lite (Sep) | 1M | Google | 19 | $0.17 | 278 | 3.04 | 4.84 | |
Motif-2-12.7B | 128k |  Motif Technologies | 19 | -- | -- | -- | -- | |
Ling-1T | 128k | InclusionAI | 19 | -- | -- | -- | -- | |
Nova Premier | 1M | Amazon | 19 | $5.00 | 28 | 2.74 | 20.29 | |
DeepSeek R1 (Jan) | 128k | DeepSeek | 19 | $2.36 | -- | -- | -- | |
Solar Pro 2 | 64k | Upstage | 19* | -- | -- | -- | -- | |
Magistral Medium 1 | 40k | Mistral | 19 | -- | -- | -- | -- | |
Mistral Medium 3 | 128k | Mistral | 19 | $0.80 | 51 | 1.37 | 11.14 | |
Llama Nemotron Super 49B v1.5 | 128k | NVIDIA | 19 | $0.17 | 51 | 1.24 | 50.05 | |
Claude 3.5 Haiku | 200k | Anthropic | 19 | $1.60 | -- | -- | -- | |
Devstral Medium | 256k | Mistral | 19 | $0.80 | 129 | 1.20 | 5.07 | |
GPT-4o (Aug) | 128k | OpenAI | 19 | $4.38 | 105 | 1.03 | 5.81 | |
Mistral Small 4 | 256k | Mistral | 19 | $0.26 | 133 | 0.72 | 4.47 | |
GPT-4o (Mar) | 128k | OpenAI | 19* | -- | -- | -- | -- | |
Gemini 2.0 Flash | 1M | Google | 19 | $0.26 | -- | -- | -- | |
Llama 3.3 Nemotron Super 49B | 128k | NVIDIA | 18* | -- | -- | -- | -- | |
Llama 4 Maverick | 1M | Meta | 18 | $0.49 | 114 | 1.02 | 5.41 | |
Qwen3 4B 2507 | 262k | Alibaba | 18 | -- | -- | -- | -- | |
Sarvam 105B (high) | 128k |  Sarvam | 18 | $0.00 | 121 | 2.40 | 23.00 | |
Magistral Small 1.2 | 128k | Mistral | 18 | $0.75 | 152 | 0.81 | 17.28 | |
Gemini 2.0 Pro Experimental | 2M | Google | 18* | -- | -- | -- | -- | |
Nova 2.0 Lite | 1M | Amazon | 18 | $0.85 | 186 | 1.02 | 3.72 | |
Devstral Small (May) | 256k | Mistral | 18 | $0.07 | -- | -- | -- | |
Claude 3 Opus | 200k | Anthropic | 18* | $30.00 | -- | -- | -- | |
Sonar Reasoning | 127k | Perplexity | 18* | -- | -- | -- | -- | |
Gemini 2.5 Flash | 1M | Google | 18* | -- | -- | -- | -- | |
Gemini 2.5 Flash-Lite | 1M | Google | 18 | $0.17 | 266 | 20.53 | 22.41 | |
Llama 3.1 405B | 128k | Meta | 17 | $3.69 | 30 | 2.16 | 19.04 | |
GPT-4o (Nov) | 128k | OpenAI | 17 | $4.38 | 113 | 0.87 | 5.30 | |
Qwen3 VL 32B | 256k | Alibaba | 17 | $1.23 | 73 | 2.64 | 9.52 | |
DeepSeek R1 Distill Qwen 32B | 128k | DeepSeek | 17* | $0.27 | 58 | 0.82 | 43.61 | |
GLM-4.6V | 128k | Z AI | 17 | $0.45 | 20 | 3.14 | 27.82 | |
Qwen3 235B | 32.8k | Alibaba | 17 | $1.23 | 47 | 2.77 | 13.52 | |
Magistral Small 1 | 40k | Mistral | 17* | -- | -- | -- | -- | |
Gemini 2.0 Flash (exp) | 1M | Google | 17* | $0.00 | -- | -- | -- | |
EXAONE 4.0 32B | 131k | LG AI Research | 17 | -- | -- | -- | -- | |
Qwen3 VL 8B | 256k | Alibaba | 17 | $0.66 | 113 | 2.31 | 24.43 | |
Nova 2.0 Omni | 1M | Amazon | 17 | $0.85 | 185 | 1.07 | 3.77 | |
Qwen3 32B | 32.8k | Alibaba | 17 | $2.63 | 99 | 2.41 | 27.58 | |
DeepSeek V3 (Dec) | 128k | DeepSeek | 16 | $0.63 | -- | -- | -- | |
DeepSeek R1 0528 Qwen3 8B | 32.8k | DeepSeek | 16* | -- | -- | -- | -- | |
Qwen3.5 2B | 262k | Alibaba | 16 | $0.04 | 348 | 0.41 | 7.59 | |
Qwen2.5 Max | 32k | Alibaba | 16* | $2.80 | 47 | 3.16 | 13.89 | |
Qwen3 14B | 32.8k | Alibaba | 16 | $1.31 | 58 | 2.83 | 45.58 | |
Nanbeige4.1-3B | 256k |  Nanbeige | 16 | -- | -- | -- | -- | |
Qwen3 VL 30B A3B | 256k | Alibaba | 16 | $0.35 | 110 | 2.20 | 6.73 | |
Solar Pro 2 | 64k | Upstage | 16* | -- | -- | -- | -- | |
Gemini 1.5 Pro (Sep) | 2M | Google | 16* | -- | -- | -- | -- | |
Ministral 3 14B | 256k | Mistral | 16 | $0.20 | 114 | 0.64 | 5.02 | |
DeepSeek R1 Distill Llama 70B | 128k | DeepSeek | 16* | $0.88 | 40 | 2.05 | 64.45 | |
Claude 3.5 Sonnet (Oct) | 200k | Anthropic | 16* | $6.00 | -- | -- | -- | |
DeepSeek R1 Distill Qwen 14B | 128k | DeepSeek | 16* | -- | -- | -- | -- | |
Falcon-H1R-7B | 256k |  TII UAE | 16 | -- | -- | -- | -- | |
Ling-flash-2.0 | 128k | InclusionAI | 16 | $0.25 | 64 | 2.27 | 10.11 | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 16 | $0.43 | 90 | 1.93 | 29.71 | |
Qwen2.5 72B | 131k | Alibaba | 16* | $0.00 | 27 | 3.44 | 21.92 | |
Sonar | 127k | Perplexity | 15* | -- | -- | -- | -- | |
Step3 VL 10B | 65.5k | StepFun | 15 | -- | -- | -- | -- | |
Qwen3 30B | 32.8k | Alibaba | 15 | $0.75 | 63 | 2.36 | 42.04 | |
Sonar Pro | 200k | Perplexity | 15* | -- | -- | -- | -- | |
Devstral Small | 256k | Mistral | 15 | $0.15 | 257 | 0.58 | 2.52 | |
QwQ 32B-Preview | 32.8k | Alibaba | 15* | $0.14 | 58 | 1.56 | 44.80 | |
Mistral Large 2 (Nov) | 128k | Mistral | 15 | $3.00 | 36 | 1.44 | 15.17 | |
GLM-4.5V | 64k | Z AI | 15 | $0.90 | 53 | 1.83 | 48.85 | |
Mistral Small 3.2 | 128k | Mistral | 15 | $0.15 | 160 | 0.57 | 3.70 | |
Llama Nemotron Ultra | 128k | NVIDIA | 15 | $0.90 | 42 | 2.52 | 62.22 | |
Qwen3 30B A3B 2507 | 262k | Alibaba | 15 | $0.35 | 65 | 2.02 | 9.77 | |
ERNIE 4.5 300B A47B | 131k | Baidu | 15 | $0.48 | 30 | 3.93 | 20.80 | |
Solar Pro 2 | 65.5k | Upstage | 15 | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 15 | $0.30 | 133 | 0.65 | 19.49 | |
Ministral 3 8B | 256k | Mistral | 15 | $0.15 | 183 | 0.55 | 3.28 | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 15 | $0.07 | 124 | 0.62 | 20.76 | |
Gemini 2.0 Flash-Lite (Feb) | 1M | Google | 15* | -- | -- | -- | -- | |
NVIDIA Nemotron 3 Nano 4B | 262k | NVIDIA | 15 | -- | -- | -- | -- | |
Qwen3.5 2B | 262k | Alibaba | 15 | $0.04 | 295 | 0.41 | 2.10 | |
Llama Nemotron Super 49B v1.5 | 128k | NVIDIA | 15 | $0.17 | 52 | 1.28 | 10.96 | |
Qwen3 32B | 32.8k | Alibaba | 15* | $1.23 | 99 | 2.43 | 7.50 | |
GPT-4o (May) | 128k | OpenAI | 14* | $7.50 | 82 | 1.01 | 7.09 | |
Llama 3.3 70B | 128k | Meta | 14 | $0.64 | 83 | 1.35 | 7.37 | |
Gemini 2.0 Flash-Lite (Preview) | 1M | Google | 14* | -- | -- | -- | -- | |
Mistral Small 3.1 | 128k | Mistral | 14 | $0.15 | 129 | 0.70 | 4.58 | |
Llama 3.1 Nemotron Nano 4B v1.1 | 128k | NVIDIA | 14* | -- | -- | -- | -- | |
Kimi Linear 48B A3B Instruct | 1M | Kimi | 14* | -- | -- | -- | -- | |
Llama 3.3 Nemotron Super 49B | 128k | NVIDIA | 14* | -- | -- | -- | -- | |
Qwen3 VL 8B | 256k | Alibaba | 14 | $0.31 | 118 | 2.33 | 6.57 | |
Qwen3 4B | 32k | Alibaba | 14* | $0.40 | 88 | 2.26 | 30.82 | |
Claude 3.5 Sonnet (June) | 200k | Anthropic | 14* | $6.00 | -- | -- | -- | |
GPT-4o (ChatGPT) | 128k | OpenAI | 14* | -- | -- | -- | -- | |
Ring-flash-2.0 | 128k | InclusionAI | 14 | $0.25 | 85 | 2.27 | 31.66 | |
Pixtral Large | 128k | Mistral | 14* | $3.00 | 49 | 1.41 | 11.60 | |
Grok 2 | 131k | xAI | 14* | -- | -- | -- | -- | |
GPT-5 nano (minimal) | 400k | OpenAI | 14 | $0.14 | 128 | 0.99 | 4.91 | |
Gemini 1.5 Flash (Sep) | 1M | Google | 14* | -- | -- | -- | -- | |
Qwen3 VL 4B | 256k | Alibaba | 14 | -- | -- | -- | -- | |
GPT-4 Turbo | 128k | OpenAI | 14* | $15.00 | 27 | 2.76 | 21.12 | |
Solar Pro 2 | 65.5k | Upstage | 14 | -- | -- | -- | -- | |
Llama 4 Scout | 10M | Meta | 14 | $0.29 | 129 | 0.76 | 4.64 | |
Nova Pro | 300k | Amazon | 13 | $1.40 | -- | -- | -- | |
Command A | 256k |  Cohere | 13 | $4.38 | 37 | 3.52 | 17.20 | |
Llama 3.1 Nemotron 70B | 128k | NVIDIA | 13 | $1.20 | 37 | 1.84 | 15.46 | |
Grok Beta | 128k | xAI | 13* | -- | -- | -- | -- | |
Qwen2.5 Instruct 32B | 128k | Alibaba | 13* | -- | -- | -- | -- | |
Qwen3 8B | 131k | Alibaba | 13 | $0.66 | 80 | 2.29 | 33.50 | |
NVIDIA Nemotron 3 Nano | 1M | NVIDIA | 13 | $0.09 | 98 | 0.44 | 5.57 | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 13 | $0.09 | 165 | 1.59 | 4.62 | |
GPT-4.1 nano | 1M | OpenAI | 13 | $0.17 | 126 | 0.71 | 4.68 | |
Mistral Large 2 (Jul) | 128k | Mistral | 13* | $3.00 | -- | -- | -- | |
Qwen3 4B 2507 | 262k | Alibaba | 13 | -- | -- | -- | -- | |
Qwen2.5 Coder 32B | 131k | Alibaba | 13* | -- | -- | -- | -- | |
Qwen3 14B | 32.8k | Alibaba | 13 | $0.61 | 60 | 2.71 | 11.06 | |
GPT-4 | 8.19k | OpenAI | 13* | $37.50 | -- | -- | -- | |
GLM-4.5V | 64k | Z AI | 13 | $0.90 | 51 | 20.77 | 30.64 | |
Mistral Small 3 | 32k | Mistral | 13* | $0.15 | 128 | 0.66 | 4.56 | |
Gemini 2.5 Flash-Lite | 1M | Google | 13 | $0.17 | 261 | 0.67 | 2.58 | |
Nova Lite | 300k | Amazon | 13 | $0.10 | 167 | 0.71 | 3.71 | |
GPT-4o mini | 128k | OpenAI | 13* | $0.26 | 36 | 3.26 | 16.96 | |
Qwen3 30B | 32.8k | Alibaba | 13 | $0.35 | 60 | 2.28 | 10.56 | |
DeepSeek-V2.5 (Dec) | 128k | DeepSeek | 13* | -- | -- | -- | -- | |
Qwen3 4B | 32k | Alibaba | 12* | $0.19 | 91 | 2.29 | 7.79 | |
Llama 3.1 70B | 128k | Meta | 12 | $0.56 | 23 | 1.71 | 23.19 | |
Sarvam 30B (high) | 65.5k | Sarvam | 12 | $0.00 | 158 | 1.90 | 17.68 | |
Gemini 2.0 Flash Thinking exp. (Dec) | 2M | Google | 12* | -- | -- | -- | -- | |
DeepSeek-V2.5 | 128k | DeepSeek | 12* | -- | -- | -- | -- | |
Claude 3 Haiku | 200k | Anthropic | 12 | $0.50 | 132 | 1.17 | 4.97 | |
Mistral Saba | 32k | Mistral | 12* | -- | -- | -- | -- | |
DeepSeek R1 Distill Llama 8B | 128k | DeepSeek | 12* | -- | -- | -- | -- | |
Gemini 1.5 Pro (May) | 2M | Google | 12* | -- | -- | -- | -- | |
R1 1776 | 128k | Perplexity | 12* | -- | -- | -- | -- | |
Qwen2.5 Turbo | 1M | Alibaba | 12* | $0.09 | 62 | 2.30 | 10.37 | |
Reka Flash | 128k |  Reka AI | 12* | $0.35 | 58 | 1.93 | 10.56 | |
Llama 3.2 90B (Vision) | 128k | Meta | 12* | $0.72 | 47 | 0.92 | 11.47 | |
Solar Mini | 4.1k | Upstage | 12* | $0.15 | -- | -- | -- | |
Llama 3.1 8B | 128k | Meta | 12 | $0.10 | 155 | 0.92 | 4.14 | |
Grok-1 | 8.19k | xAI | 12* | -- | -- | -- | -- | |
Qwen2 72B | 131k | Alibaba | 12* | -- | -- | -- | -- | |
EXAONE 4.0 32B | 131k | LG AI Research | 12 | -- | -- | -- | -- | |
Ministral 3 3B | 256k | Mistral | 11 | $0.10 | 254 | 0.45 | 2.42 | |
Gemini 1.5 Flash-8B | 1.05M | Google | 11* | -- | -- | -- | -- | |
Jamba 1.7 Large | 256k |  AI21 Labs | 11 | $3.50 | 59 | 1.34 | 9.88 | |
Granite 4.0 H Small | 128k | IBM | 11 | $0.11 | 455 | 10.24 | 11.34 | |
Jamba 1.5 Large | 256k | AI21 Labs | 11* | $3.50 | -- | -- | -- | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 11 | $0.43 | 94 | 1.85 | 7.15 | |
Qwen3 8B | 32.8k | Alibaba | 11 | $0.31 | 82 | 2.19 | 8.30 | |
DeepSeek-Coder-V2 | 128k | DeepSeek | 11* | -- | -- | -- | -- | |
Jamba 1.6 Large | 256k | AI21 Labs | 11* | $3.50 | 60 | 1.38 | 9.74 | |
Qwen3.5 0.8B | 262k | Alibaba | 11 | $0.02 | 409 | 0.33 | 6.44 | |
LFM2 24B A2B | 32.8k |  Liquid AI | 10 | $0.05 | 63 | 0.43 | 8.40 | |
Gemini 1.5 Flash (May) | 1M | Google | 10* | -- | -- | -- | -- | |
Phi-4 | 16k |  Microsoft Azure | 10 | $0.22 | 34 | 2.08 | 16.87 | |
Gemma 3 27B | 128k | Google | 10 | $0.00 | 29 | 2.04 | 19.15 | |
Claude 3 Sonnet | 200k | Anthropic | 10* | $6.00 | -- | -- | -- | |
Nova Micro | 130k | Amazon | 10 | $0.06 | 311 | 0.66 | 2.26 | |
Mistral Small (Sep) | 32.8k | Mistral | 10* | $0.30 | 121 | 0.68 | 4.81 | |
Gemini 1.0 Ultra | 32.8k | Google | 10* | -- | -- | -- | -- | |
Phi-3 Mini | 4.1k | Microsoft Azure | 10* | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 10 | $0.30 | 137 | 1.22 | 4.87 | |
Gemma 3n E4B (May) | 32k | Google | 10* | -- | -- | -- | -- | |
Phi-4 Multimodal | 128k | Microsoft Azure | 10* | $0.00 | 17 | 0.86 | 30.09 | |
Qwen2.5 Coder 7B | 131k | Alibaba | 10* | -- | -- | -- | -- | |
Qwen3.5 0.8B | 262k | Alibaba | 10 | $0.02 | 404 | 0.35 | 1.58 | |
Mistral Large (Feb) | 32.8k | Mistral | 10* | $6.00 | -- | -- | -- | |
Mixtral 8x22B | 65.4k | Mistral | 10* | -- | -- | -- | -- | |
Llama 2 Chat 7B | 4.1k | Meta | 10* | $0.10 | -- | -- | -- | |
Llama 3.2 3B | 128k | Meta | 10* | $0.08 | 51 | 0.87 | 10.58 | |
Jamba Reasoning 3B | 262k | AI21 Labs | 10 | -- | -- | -- | -- | |
Qwen3 VL 4B | 256k | Alibaba | 10 | -- | -- | -- | -- | |
Qwen1.5 Chat 110B | 32k | Alibaba | 10* | -- | -- | -- | -- | |
Reka Flash 3 | 128k | Reka AI | 10 | $0.35 | -- | -- | -- | |
Claude 2.1 | 200k | Anthropic | 9* | -- | -- | -- | -- | |
Ling-mini-2.0 | 131k | InclusionAI | 9 | -- | -- | -- | -- | |
DeepSeek R1 Distill Qwen 1.5B | 128k | DeepSeek | 9* | -- | -- | -- | -- | |
DeepSeek-V2 | 128k | DeepSeek | 9* | -- | -- | -- | -- | |
Claude 2.0 | 100k | Anthropic | 9* | -- | -- | -- | -- | |
Mistral Small (Feb) | 32.8k | Mistral | 9* | $1.50 | 123 | 0.70 | 4.75 | |
Mistral Medium | 32.8k | Mistral | 9* | $4.09 | 54 | 1.64 | 10.82 | |
GPT-3.5 Turbo | 4.1k | OpenAI | 9* | $0.75 | -- | -- | -- | |
Llama 3 70B | 8.19k | Meta | 9 | $0.87 | -- | -- | -- | |
Arctic | 4k |  Snowflake | 9* | -- | -- | -- | -- | |
Qwen Chat 72B | 33.8k | Alibaba | 9* | -- | -- | -- | -- | |
Gemma 3 12B | 128k | Google | 9 | $0.00 | 30 | 31.38 | 48.32 | |
LFM 40B | 32k | Liquid AI | 9* | -- | -- | -- | -- | |
Llama 3.2 11B (Vision) | 128k | Meta | 9 | $0.16 | 51 | 0.58 | 10.31 | |
PALM-2 | 8k | Google | 9* | -- | -- | -- | -- | |
Gemini 1.0 Pro | 32.8k | Google | 9* | -- | -- | -- | -- | |
DeepSeek Coder V2 Lite | 128k | DeepSeek | 8* | -- | -- | -- | -- | |
Phi-4 Mini | 128k | Microsoft Azure | 8 | $0.00 | 43 | 0.81 | 12.38 | |
Sarvam M | 32.8k | Sarvam | 8 | -- | -- | -- | -- | |
Llama 2 Chat 70B | 4.1k | Meta | 8* | -- | -- | -- | -- | |
DeepSeek LLM 67B (V1) | 4.1k | DeepSeek | 8* | -- | -- | -- | -- | |
Llama 2 Chat 13B | 4.1k | Meta | 8* | -- | -- | -- | -- | |
Command-R+ (Apr) | 128k | Cohere | 8* | $6.00 | -- | -- | -- | |
OpenChat 3.5 | 8.19k |  OpenChat | 8* | -- | -- | -- | -- | |
DBRX | 32.8k |  Databricks | 8* | -- | -- | -- | -- | |
Exaone 4.0 1.2B | 64k | LG AI Research | 8 | -- | -- | -- | -- | |
Exaone 4.0 1.2B | 64k | LG AI Research | 8 | -- | -- | -- | -- | |
LFM2.5-1.2B-Thinking | 32k | Liquid AI | 8 | -- | -- | -- | -- | |
Jamba 1.7 Mini | 258k | AI21 Labs | 8 | -- | -- | -- | -- | |
LFM2.5-1.2B-Instruct | 32k | Liquid AI | 8 | $0.00 | -- | -- | -- | |
LFM2 2.6B | 32.8k | Liquid AI | 8 | $0.00 | -- | -- | -- | |
Jamba 1.5 Mini | 256k | AI21 Labs | 8* | $0.25 | -- | -- | -- | |
Granite 4.0 H 1B | 128k | IBM | 8 | -- | -- | -- | -- | |
Qwen3 1.7B | 32k | Alibaba | 8 | $0.40 | 124 | 1.72 | 21.91 | |
Jamba 1.6 Mini | 256k | AI21 Labs | 8* | $0.25 | 178 | 0.81 | 3.62 | |
Mixtral 8x7B | 32.8k | Mistral | 8* | $0.54 | -- | -- | -- | |
Gemma 3 270M | 32k | Google | 8 | -- | -- | -- | -- | |
Apertus 70B Instruct | 65.5k |  Swiss AI Initiative | 8 | $1.34 | 62 | 2.87 | 10.97 | |
Granite 4.0 Micro | 128k | IBM | 8 | -- | -- | -- | -- | |
Qwen Chat 14B | 8.19k | Alibaba | 7* | -- | -- | -- | -- | |
Llama 65B | 2.05k | Meta | 7* | -- | -- | -- | -- | |
Claude Instant | 100k | Anthropic | 7* | -- | -- | -- | -- | |
Command-R (Mar) | 128k | Cohere | 7* | $0.75 | -- | -- | -- | |
Mistral 7B | 8.19k | Mistral | 7* | $0.25 | 170 | 0.53 | 3.46 | |
Granite 4.0 1B | 128k | IBM | 7 | -- | -- | -- | -- | |
LFM2 8B A1B | 32.8k | Liquid AI | 7 | $0.00 | -- | -- | -- | |
Granite 3.3 8B | 128k | IBM | 7 | $0.09 | 323 | 9.53 | 11.08 | |
Qwen3 1.7B | 32k | Alibaba | 7 | $0.19 | 124 | 1.71 | 5.75 | |
Qwen3 0.6B | 32k | Alibaba | 6 | $0.40 | 175 | 1.58 | 15.89 | |
Llama 3 8B | 8.19k | Meta | 6 | $0.07 | -- | -- | -- | |
Gemma 3n E4B | 32k | Google | 6 | $0.03 | 24 | 1.10 | 21.74 | |
LFM2 1.2B | 32.8k | Liquid AI | 6 | $0.00 | -- | -- | -- | |
Gemma 3 4B | 128k | Google | 6 | $0.00 | 30 | 1.55 | 18.02 | |
Llama 3.2 1B | 128k | Meta | 6 | $0.05 | 86 | 0.95 | 6.74 | |
LFM2.5-VL-1.6B | 32k | Liquid AI | 6 | $0.00 | -- | -- | -- | |
Granite 4.0 350M | 32.8k | IBM | 6 | -- | -- | -- | -- | |
Apertus 8B Instruct | 65.5k | Swiss AI Initiative | 6 | $0.13 | 131 | 2.37 | 6.19 | |
Qwen3 0.6B | 32k | Alibaba | 6 | $0.19 | 176 | 1.56 | 4.41 | |
Gemma 3 1B | 32k | Google | 6 | $0.00 | 38 | 0.78 | 13.78 | |
Granite 4.0 H 350M | 32.8k | IBM | 5 | -- | -- | -- | -- | |
Gemma 3n E2B | 32k | Google | 5 | $0.00 | -- | -- | -- | |
Tiny Aya Global | 8.19k | Cohere | 5 | -- | -- | -- | -- | |
Gemini 3 Deep Think | 128k | Google | -- | -- | -- | -- | -- | |
GPT-5.4 Pro (xhigh) | 1.05M | OpenAI | -- | $67.50 | -- | -- | -- | |
Mi:dm K 2.5 Pro Preview | 128k | Korea Telecom | -- | -- | -- | -- | -- | |
GPT-3.5 Turbo (0613) | 4.1k | OpenAI | -- | -- | -- | -- | -- | |
GPT-4o Realtime (Dec) | 128k | OpenAI | -- | -- | -- | -- | -- | |
GPT-4o mini Realtime (Dec) | 128k | OpenAI | -- | -- | -- | -- | -- | |
Key definitions
Frequently Asked Questions
Gemini 3.1 Pro Preview currently ranks #1 on the Artificial Analysis LLM Leaderboard with an Intelligence Index score of 57, out of 299 models ranked.
The top models by Intelligence Index are: 1. Gemini 3.1 Pro Preview (57), 2. GPT-5.4 (xhigh) (57), 3. GPT-5.3 Codex (xhigh) (54), 4. Claude Opus 4.6 (Adaptive Reasoning, Max Effort) (53), 5. Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) (52).
Mercury 2 is the fastest at 835.1 tokens per second, followed by Granite 4.0 H Small (455.1 t/s) and Qwen3.5 0.8B (Reasoning) (409.5 t/s).
Qwen3.5 0.8B (Non-reasoning) is the most affordable at $0.02 per 1M tokens (blended 3:1 input-to-output), followed by Qwen3.5 0.8B (Reasoning) ($0.02) and Gemma 3n E4B Instruct ($0.03).
GLM-5 (Reasoning) is the highest-ranked open weights model with an Intelligence Index score of 50. There are 186 open weights models out of 299 total on the leaderboard.
The top open weights models by Intelligence Index are: 1. GLM-5 (Reasoning) (50), 2. Kimi K2.5 (Reasoning) (47), 3. Qwen3.5 397B A17B (Reasoning) (45).
Gemini 3.1 Pro Preview leads among 147 reasoning models with an Intelligence Index score of 57. Reasoning models use extended thinking to solve complex problems before responding.
The leaderboard includes filters to narrow results by model type (reasoning vs non-reasoning), openness (open weights vs proprietary), and other criteria. You can also adjust prompt options to see how performance varies with different input lengths.
Click on any model name in the leaderboard to visit its dedicated comparison page with detailed charts covering intelligence, pricing, speed, latency, and more. You can also compare API providers for each model. View all models