LLM leaderboard
Every tracked language model by intelligence, with what it costs and how fast it answers.
ranked by intelligence · 611 models · updated Aug 30 · 151–200
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 151 | GLM-5 (Non-reasoning) | Z AI | 33.20 | $1 | $3.2 | 63 |
| 152 | Qwen3.5 122B A10B (Reasoning) | Alibaba | 32.80 | $0.4 | $3.2 | 132 |
| 153 | DeepSeek V3.2 (Reasoning) | DeepSeek | 32.80 | $0.28 | $0.42 | — |
| 154 | Qwen3.5 397B A17B (Non-reasoning) | Alibaba | 32.70 | $0.6 | $3.6 | 78 |
| 155 | Qwen3 Max Thinking | Alibaba | 32.50 | — | — | — |
| 156 | MiniMax-M2.1 | MiniMax | 32.10 | $0.3 | $1.2 | 85 |
| 157 | Qwen3.6 35B A3B (Reasoning) | Alibaba | 32.10 | $0.38 | $2.25 | 123 |
| 158 | DeepSeek V4 Pro (Non-reasoning) | DeepSeek | 31.90 | $0.43 | $0.87 | 68 |
| 159 | GPT-5 (low) | OpenAI | 31.90 | $1.25 | $10 | 74 |
| 160 | MiMo-V2-Flash (Reasoning) | Xiaomi | 31.90 | $0.1 | $0.3 | — |
| 161 | Claude 4 Opus (Reasoning) | Anthropic | 31.70 | $15 | $75 | — |
| 162 | Ring-2.6-1T | InclusionAI | 31.70 | $0.3 | $2.5 | 129 |
| 163 | GPT-5 mini (medium) | OpenAI | 31.60 | $0.25 | $2 | 90 |
| 164 | DeepSeek V3.1 Terminus (Reasoning) | DeepSeek | 31.40 | $1.64 | $2.75 | — |
| 165 | Qwen3.5 Omni Plus | Alibaba | 31.30 | $0.4 | $4.8 | 129 |
| 166 | Grok 4.1 Fast (Reasoning) | SpaceXAI | 31.30 | — | — | — |
| 167 | Qwen3.6 27B (Non-reasoning) | Alibaba | 31.30 | $0.6 | $3.6 | 55 |
| 168 | GPT-5.1 Codex mini (high) | OpenAI | 31.30 | $0.25 | $2 | — |
| 169 | o3 | OpenAI | 31.10 | $2 | $8 | 111 |
| 170 | K-EXAONE 2.0 | LG AI Research | 31.00 | — | — | — |
| 171 | Step 3.7 Flash | StepFun | 30.90 | $0.2 | $1.15 | 87 |
| 172 | GPT-5.4 nano (medium) | OpenAI | 30.80 | $0.2 | $1.25 | 172 |
| 173 | GPT-5.4 mini (medium) | OpenAI | 30.50 | $0.75 | $4.5 | 190 |
| 174 | Mistral Medium 3.5 | Mistral | 30.40 | $1.5 | $7.5 | 142 |
| 175 | Kimi K2.5 (Non-reasoning) | Kimi | 30.10 | $0.6 | $3 | 71 |
| 176 | Qwen3.5 27B (Non-reasoning) | Alibaba | 30.00 | $0.3 | $2.4 | 83 |
| 177 | Qwen3.5 35B A3B (Reasoning) | Alibaba | 29.90 | $0.25 | $2 | 146 |
| 178 | Claude 4.5 Sonnet (Non-reasoning) | Anthropic | 29.90 | $3 | $15 | 46 |
| 179 | Claude 4.5 Haiku (Reasoning) | Anthropic | 29.90 | $1 | $5 | 126 |
| 180 | Claude 4 Sonnet (Reasoning) | Anthropic | 29.80 | $3 | $15 | — |
| 181 | Gemma 4 31B (Reasoning) | 29.70 | $0 | $0 | 35 | |
| 182 | GLM-4.6 (Reasoning) | Z AI | 29.30 | $0.55 | $2.2 | 50 |
| 183 | DeepSeek V4 Flash (Non-reasoning) | DeepSeek | 29.30 | $0.09 | $0.2 | — |
| 184 | GPT-5.5 Instant (June 2026) | OpenAI | 29.20 | $5 | $30 | 148 |
| 185 | JT-35B-Flash | China Mobile | 29.00 | — | — | — |
| 186 | MiniMax-M2 | MiniMax | 28.90 | $0.3 | $1.2 | 96 |
| 187 | KAT-Coder-Pro V1 | KwaiKAT | 28.90 | — | — | — |
| 188 | Claude 4.1 Opus (Non-reasoning) | Anthropic | 28.80 | $15 | $75 | — |
| 189 | MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 28.40 | $0.43 | $0.87 | 32 |
| 190 | GPT-5.4 (Non-reasoning) | OpenAI | 28.30 | $2.5 | $15 | 104 |
| 191 | Qwen3.5 122B A10B (Non-reasoning) | Alibaba | 28.20 | $0.4 | $3.2 | 145 |
| 192 | Grok 4 Fast (Reasoning) | SpaceXAI | 27.90 | $0.2 | $0.5 | — |
| 193 | Gemini 3 Flash Preview (Non-reasoning) | 27.90 | $0.5 | $3 | 184 | |
| 194 | Claude 3.7 Sonnet (Reasoning) | Anthropic | 27.60 | — | — | — |
| 195 | GLM-4.7 (Non-reasoning) | Z AI | 27.10 | $0.6 | $2.2 | 73 |
| 196 | GPT-5.6 Luna (Non-reasoning) | OpenAI | 26.80 | $0.2 | $1.2 | 108 |
| 197 | Ling-2.6-1T | InclusionAI | 26.60 | $0.3 | $2.5 | — |
| 198 | Hy3-preview (Non-reasoning) | Tencent | 26.60 | $0.06 | $0.21 | — |
| 199 | Step 3.5 Flash 2603 | StepFun | 26.50 | $0.1 | $0.3 | 224 |
| 200 | Doubao Seed Code | ByteDance Seed | 26.50 | — | — | — |
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.