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 · 251–300
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 251 | MiniMax-M2 | MiniMax | 18.60 | $0.3 | $1.2 | 66 |
| 252 | KAT-Coder-Pro V1 | KwaiKAT | 18.60 | — | — | — |
| 253 | GPT-6 Luna (Non-reasoning) | OpenAI | 18.50 | $0.1 | $0.5 | 111 |
| 254 | GLM-4.6 (Reasoning) | Z AI | 18.50 | $0.55 | $2.2 | 35 |
| 255 | Qwen3.5 397B A17B (Reasoning) | Alibaba | 18.40 | $0.6 | $3.6 | 56 |
| 256 | MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 18.30 | $0.435 | $0.87 | 32 |
| 257 | GPT-5.4 (Non-reasoning) | OpenAI | 18.20 | $2.5 | $15 | 65 |
| 258 | Qwen3.6 35B A3B (Reasoning) | Alibaba | 18.20 | $0.375 | $2.25 | 127 |
| 259 | Grok 4 Fast (Reasoning) | SpaceXAI | 17.90 | $0.2 | $0.5 | — |
| 260 | Gemini 3 Flash Preview (Non-reasoning) | 17.90 | $0.5 | $3 | 195 | |
| 261 | Qwen3.5 122B A10B (Non-reasoning) | Alibaba | 17.70 | $0.4 | $3.2 | 142 |
| 262 | Claude 3.7 Sonnet (Reasoning) | Anthropic | 17.70 | — | — | — |
| 263 | Muse Glimmer (High) | Meta | 17.50 | $0.3 | $1.2 | 124 |
| 264 | GLM-4.7 (Non-reasoning) | Z AI | 17.40 | $0.6 | $2.2 | 37 |
| 265 | Step 3.5 Flash 2603 | StepFun | 17.00 | $0.1 | $0.3 | 142 |
| 266 | Ling-2.6-1T | InclusionAI | 17.00 | $0.3 | $2.5 | — |
| 267 | GPT-5.2 (Non-reasoning) | OpenAI | 17.00 | $1.75 | $14 | 69 |
| 268 | Hy3-preview (Non-reasoning) | Tencent | 17.00 | $0.063 | $0.21 | — |
| 269 | Doubao Seed Code | ByteDance Seed | 16.90 | — | — | — |
| 270 | Claude 4.5 Haiku (Reasoning) | Anthropic | 16.90 | $1 | $5 | 86 |
| 271 | GPT-5 mini (High) | OpenAI | 16.80 | $0.25 | $2 | 147 |
| 272 | Gemma 4 26B A4B (Reasoning) | 16.70 | $0.1 | $0.4 | 65 | |
| 273 | o4-mini (High) | OpenAI | 16.70 | $1.1 | $4.4 | 149 |
| 274 | Claude 4 Opus (Non-reasoning) | Anthropic | 16.60 | $15 | $75 | — |
| 275 | DeepSeek V3.2 Exp (Reasoning) | DeepSeek | 16.60 | $0.28 | $0.42 | — |
| 276 | Step 3.5 Flash | StepFun | 16.60 | $0.1 | $0.3 | 138 |
| 277 | Claude 4 Sonnet (Non-reasoning) | Anthropic | 16.60 | — | — | — |
| 278 | Ring-2.6-1T | InclusionAI | 16.60 | $0.3 | $2.5 | 114 |
| 279 | Qwen3 Max Thinking (Preview) | Alibaba | 16.30 | — | — | — |
| 280 | Gemini 2.5 Pro | 16.10 | $1.25 | $10 | 110 | |
| 281 | DeepSeek V3.2 (Non-reasoning) | DeepSeek | 16.00 | $0.28 | $0.42 | — |
| 282 | MiMo-V2-Flash (Non-reasoning) | Xiaomi | 16.00 | — | — | — |
| 283 | Qwen3.5 122B A10B (Reasoning) | Alibaba | 15.60 | $0.4 | $3.2 | 127 |
| 284 | K2 Horizon 3.7B | Institute of Foundation Models | 15.60 | — | — | — |
| 285 | Gemini 3.1 Flash-Lite | 15.60 | $0.25 | $1.5 | 342 | |
| 286 | Qwen3 Max | Alibaba | 15.60 | — | — | — |
| 287 | Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | 15.50 | — | — | — | |
| 288 | GPT-5.6 Luna (Non-reasoning) | OpenAI | 15.50 | $0.2 | $1.2 | 118 |
| 289 | Claude 4.5 Haiku (Non-reasoning) | Anthropic | 15.40 | $1 | $5 | 88 |
| 290 | Kimi K2 0905 | Kimi | 15.30 | $0.6 | $2.5 | 56 |
| 291 | Claude 3.7 Sonnet (Non-reasoning) | Anthropic | 15.30 | $3 | $15 | — |
| 292 | o1 | OpenAI | 15.20 | $15 | $60 | — |
| 293 | Qwen3.6 35B A3B (Non-reasoning) | Alibaba | 15.20 | $0.375 | $2.25 | 135 |
| 294 | Qwen3.5 35B A3B (Non-reasoning) | Alibaba | 15.10 | $0.25 | $2 | 162 |
| 295 | Gemini 2.5 Pro Preview (Mar' 25) | 15.00 | — | — | — | |
| 296 | GLM-4.7-Flash (Reasoning) | Z AI | 14.90 | $0.07 | $0.4 | 69 |
| 297 | GLM-4.6 (Non-reasoning) | Z AI | 14.90 | $0.575 | $2.2 | 32 |
| 298 | DeepSeek V3.1 Terminus (Reasoning) | DeepSeek | 14.80 | $1.635 | $2.75 | — |
| 299 | Gemma 4 31B (Reasoning) | 14.70 | $0 | $0 | 36 | |
| 300 | Grok 4.20 0309 (Non-reasoning) | SpaceXAI | 14.60 | $2 | $6 | — |
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.