LLM leaderboard
Every tracked language model by intelligence, with what it costs and how fast it answers.
ranked by intelligence · 690 models · updated Oct 15 · 201–250
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 201 | Grok 4 | SpaceXAI | 22.50 | $3 | $15 | 74 |
| 202 | MiMo-V2-Flash (Feb 2026) | Xiaomi | 22.40 | — | — | — |
| 203 | GLM-5.2 (Non-reasoning) | Z AI | 22.40 | $1.4 | $4.4 | 138 |
| 204 | Gemini 3 Pro Preview (Low) | 22.30 | $2 | $12 | — | |
| 205 | Gemini 3.5 Flash-Lite | 22.20 | $0.3 | $2.5 | 435 | |
| 206 | GLM-4.7 (Reasoning) | Z AI | 22.20 | $0.6 | $2.2 | 38 |
| 207 | Kimi K2 Thinking | Kimi | 22.00 | $0.6 | $2.5 | 158 |
| 208 | o3-pro | OpenAI | 21.90 | $20 | $80 | — |
| 209 | MiMo-V2.5 | Xiaomi | 21.80 | $0.14 | $0.28 | 33 |
| 210 | G9v3-39A5B | AI9Stars | 21.80 | $0 | $0 | — |
| 211 | GLM-5 (Non-reasoning) | Z AI | 21.80 | $1 | $3.2 | 73 |
| 212 | KAT Coder Pro V2 | KwaiKAT | 21.70 | $0.3 | $1.2 | — |
| 213 | A.X-K2 | SK Telecom | 21.50 | — | — | — |
| 214 | GPT-6 Luna (Low) | OpenAI | 21.50 | $0.1 | $0.5 | 119 |
| 215 | DeepSeek V3.2 (Reasoning) | DeepSeek | 21.50 | $0.28 | $0.42 | — |
| 216 | Qwen3.5 397B A17B (Non-reasoning) | Alibaba | 21.40 | $0.6 | $3.6 | 56 |
| 217 | Qwen3.6 27B (Reasoning) | Alibaba | 21.40 | $0.6 | $3.6 | 56 |
| 218 | Qwen3 Max Thinking | Alibaba | 21.30 | — | — | — |
| 219 | GPT-5.6 Luna (Low) | OpenAI | 21.00 | $0.2 | $1.2 | 120 |
| 220 | MiniMax-M2.1 | MiniMax | 20.90 | $0.3 | $1.2 | 62 |
| 221 | DeepSeek V4 Pro 0424 (Non-reasoning) | DeepSeek | 20.80 | $0.435 | $0.87 | 95 |
| 222 | GPT-5 (Low) | OpenAI | 20.80 | $1.25 | $10 | 93 |
| 223 | GPT-5.6 Terra (Non-reasoning) | OpenAI | 20.80 | $2 | $12 | 90 |
| 224 | MiMo-V2-Flash (Reasoning) | Xiaomi | 20.80 | $0.1 | $0.3 | — |
| 225 | Claude 4.5 Sonnet (Reasoning) | Anthropic | 20.70 | $3 | $15 | 44 |
| 226 | GPT-5.4 nano (Xhigh) | OpenAI | 20.70 | $0.2 | $1.25 | 166 |
| 227 | K2 Horizon 7B | Institute of Foundation Models | 20.60 | — | — | — |
| 228 | Claude 4 Opus (Reasoning) | Anthropic | 20.60 | $15 | $75 | — |
| 229 | GPT-5 mini (Medium) | OpenAI | 20.60 | $0.25 | $2 | 137 |
| 230 | Qwen3.5 Omni Plus | Alibaba | 20.40 | $0.4 | $4.8 | 88 |
| 231 | Grok 4.1 Fast (Reasoning) | SpaceXAI | 20.40 | — | — | — |
| 232 | DeepSeek V4 Pro 0813 (Non-reasoning) | DeepSeek | 20.40 | $1.32 | $3.96 | 94 |
| 233 | GPT-5.1 Codex mini (High) | OpenAI | 20.40 | $0.25 | $2 | 175 |
| 234 | o3 | OpenAI | 20.20 | $2 | $8 | 112 |
| 235 | Qwen3.8 27B (Non-reasoning) | Alibaba | 20.20 | $0.5 | $3 | 45 |
| 236 | Ling 3.0 Flash | InclusionAI | 20.10 | $0.075 | $0.22 | 290 |
| 237 | GPT-5.4 nano (Medium) | OpenAI | 20.00 | $0.2 | $1.25 | 161 |
| 238 | Qwen3.6 27B (Non-reasoning) | Alibaba | 19.80 | $0.6 | $3.6 | 56 |
| 239 | K-EXAONE 2.0 0803 | LG AI Research | 19.70 | — | — | — |
| 240 | GPT-5.4 mini (Medium) | OpenAI | 19.70 | $0.75 | $4.5 | 205 |
| 241 | Step 3.7 Flash | StepFun | 19.50 | $0.2 | $1.15 | 190 |
| 242 | Qwen3.5 27B (Non-reasoning) | Alibaba | 19.40 | $0.3 | $2.4 | 84 |
| 243 | Kimi K2.5 (Non-reasoning) | Kimi | 19.40 | $0.6 | $3 | 57 |
| 244 | Qwen3.5 35B A3B (Reasoning) | Alibaba | 19.30 | $0.25 | $2 | 147 |
| 245 | Claude 4.5 Sonnet (Non-reasoning) | Anthropic | 19.30 | $3 | $15 | 41 |
| 246 | LongCat 2.0 | LongCat | 19.10 | $0.75 | $2.95 | 69 |
| 247 | Claude 4 Sonnet (Reasoning) | Anthropic | 18.90 | — | — | — |
| 248 | DeepSeek V4 Flash 0420 (Non-reasoning) | DeepSeek | 18.90 | $0.0938 | $0.1876 | — |
| 249 | JT-35B-Flash | China Mobile | 18.70 | — | — | — |
| 250 | Claude 4.1 Opus (Non-reasoning) | Anthropic | 18.60 | $15 | $75 | — |
what intelligence means
A composite of nine independent evaluations covering reasoning, coding, agentic work and knowledge. Higher is better. It is versioned, so scores are comparable within a version rather than across all time.