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 · 151–200
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 151 | Gemini 3 Flash Preview (Reasoning) | 26.30 | $0.5 | $3 | 184 | |
| 152 | Qwen3.8 27B (Low) | Alibaba | 26.20 | $0.5 | $3 | 45 |
| 153 | GLM-5.1 (Reasoning) | Z AI | 26.10 | $1.285 | $4.07 | 67 |
| 154 | MiMo-V2.5-Pro (Reasoning) | Xiaomi | 26.00 | $0.435 | $0.87 | 38 |
| 155 | GPT-5.5 Instant (June 2026) | OpenAI | 26.00 | $5 | $30 | 152 |
| 156 | Kimi K2.7 Code | Kimi | 25.80 | $0.95 | $4 | 58 |
| 157 | Inkling Small | Thinking Machines | 25.70 | $0.3 | $1.2 | 190 |
| 158 | Grok 4.20 0309 v2 (Reasoning) | SpaceXAI | 25.70 | $1.25 | $2.5 | 106 |
| 159 | K2 Horizon MoVA 36B A4B | Institute of Foundation Models | 25.30 | — | — | — |
| 160 | Hy3 | Tencent | 25.30 | $0.136 | $0.555 | 85 |
| 161 | Grok 4.20 0309 (Reasoning) | SpaceXAI | 25.20 | $2 | $6 | — |
| 162 | Qwen3.7 Plus | Alibaba | 25.20 | $0.4 | $1.6 | 56 |
| 163 | MiMo-V2-Omni-0327 | Xiaomi | 25.10 | — | — | — |
| 164 | Inkling (Xhigh) | Thinking Machines | 25.00 | $1 | $4.05 | 178 |
| 165 | GPT-5.6 Luna (Medium) | OpenAI | 25.00 | $0.2 | $1.2 | 122 |
| 166 | GPT-5 Codex (High) | OpenAI | 24.90 | $1.25 | $10 | 166 |
| 167 | Grok 4.3 (High) | SpaceXAI | 24.90 | $1.25 | $2.5 | 95 |
| 168 | Grok 4.3 (Medium) | SpaceXAI | 24.80 | $1.25 | $2.5 | 100 |
| 169 | Claude Sonnet 4.6 (Non-reasoning, High) | Anthropic | 24.70 | $3 | $15 | 45 |
| 170 | GPT-5.1 (High) | OpenAI | 24.70 | $1.25 | $10 | 112 |
| 171 | DeepSeek V4.1 Flash (Non-reasoning) | DeepSeek | 24.70 | $0.3 | $1.2 | 167 |
| 172 | Solar Open2 250B | Upstage | 24.70 | — | — | — |
| 173 | Ling-3.0-flash-VL | InclusionAI | 24.60 | — | — | — |
| 174 | DeepSeek V4 Flash 0420 (High) | DeepSeek | 24.40 | $0.1119 | $0.2338 | 43 |
| 175 | Claude Sonnet 5 (Low) | Anthropic | 24.30 | $2 | $10 | 58 |
| 176 | Grok 4.3 (Low) | SpaceXAI | 24.30 | $1.25 | $2.5 | 89 |
| 177 | GLM-5.1 (Non-reasoning) | Z AI | 24.20 | $1.38 | $4.4 | 71 |
| 178 | DeepSeek V4 Flash 0420 (Max) | DeepSeek | 24.20 | $0.1119 | $0.2338 | 40 |
| 179 | Solar Mini 4 | Upstage | 24.10 | $0.1 | $0.4 | 84 |
| 180 | GPT-5.4 mini (Xhigh) | OpenAI | 24.10 | $0.75 | $4.5 | 233 |
| 181 | MiMo-V2-Omni | Xiaomi | 23.90 | — | — | — |
| 182 | Gemini 3.5 Flash (Minimal) | 23.80 | $1.5 | $9 | 176 | |
| 183 | GPT-5.1 Codex (High) | OpenAI | 23.70 | $1.25 | $10 | 126 |
| 184 | Claude Opus 4.5 (Non-reasoning) | Anthropic | 23.70 | $5 | $25 | 46 |
| 185 | Kimi K2.6 (Non-reasoning) | Kimi | 23.60 | $0.95 | $4 | 45 |
| 186 | GLM 5V Turbo (Reasoning) | Z AI | 23.50 | — | — | — |
| 187 | Kimi K2.5 (Reasoning) | Kimi | 23.50 | $0.6 | $2.75 | 60 |
| 188 | Claude Sonnet 4.6 (Non-reasoning, Low) | Anthropic | 23.30 | $3 | $15 | 44 |
| 189 | GPT-5.5 (Non-reasoning) | OpenAI | 23.20 | $5 | $30 | 74 |
| 190 | Claude Sonnet 5 (Non-reasoning, High) | Anthropic | 23.20 | $2 | $10 | 58 |
| 191 | GPT-5 (High) | OpenAI | 23.00 | $1.25 | $10 | 102 |
| 192 | Qwen3.5 27B (Reasoning) | Alibaba | 22.90 | $0.3 | $2.4 | 77 |
| 193 | Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 22.90 | $0.6 | $2.5 | 156 |
| 194 | GPT-5 (Medium) | OpenAI | 22.90 | $1.25 | $10 | 95 |
| 195 | MiniMax-M2.5 | MiniMax | 22.80 | $0.3 | $1.2 | 67 |
| 196 | MiniMax-M2.7 | MiniMax | 22.80 | $0.3 | $1.2 | 58 |
| 197 | Claude 4.1 Opus (Reasoning) | Anthropic | 22.80 | $15 | $75 | — |
| 198 | Hy3-preview (Reasoning) | Tencent | 22.70 | $0.063 | $0.21 | — |
| 199 | GPT-5.5 Instant (May 2026) | OpenAI | 22.70 | $5 | $30 | — |
| 200 | Ling-3.0-flash-Fin | InclusionAI | 22.60 | $0.075 | $0.22 | 272 |
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.