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 · 101–150
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 101 | GLM-5.2 (Max) | Z AI | 33.70 | $1.4 | $4.4 | 81 |
| 102 | Gemini 3.5 Flash (Medium) | 33.60 | $1.5 | $9 | 179 | |
| 103 | Motif 3 | Motif Technologies | 33.60 | — | — | — |
| 104 | GPT-5.6 Sol (Low) | OpenAI | 33.50 | $4 | $20 | 74 |
| 105 | Gemini 3.8 Flash (Low) | 33.50 | $0.75 | $3.75 | — | |
| 106 | GPT-6 Luna (High) | OpenAI | 32.90 | $0.1 | $0.5 | 119 |
| 107 | Gemini 3.5 Flash (High) | 32.60 | $1.5 | $9 | 177 | |
| 108 | GPT-5.3 Codex (Xhigh) | OpenAI | 32.50 | $1.75 | $14 | 99 |
| 109 | Motif 3 (Beta) | Motif Technologies | 32.30 | — | — | — |
| 110 | GPT-5.6 Luna (High) | OpenAI | 32.10 | $0.2 | $1.2 | 115 |
| 111 | Claude Opus 4.6 (Max) | Anthropic | 31.90 | $5 | $25 | 39 |
| 112 | Claude Sonnet 5 (High) | Anthropic | 31.70 | $2 | $10 | 59 |
| 113 | Muse Spark | Meta | 31.30 | — | — | — |
| 114 | Claude Opus 4.7 (Non-reasoning, High) | Anthropic | 30.90 | $5 | $25 | 43 |
| 115 | GPT-5.5 (Low) | OpenAI | 30.70 | $5 | $30 | 83 |
| 116 | K2 Horizon 375B A23B | Institute of Foundation Models | 30.50 | $0 | $0 | 480 |
| 117 | GPT-5.2 (Xhigh) | OpenAI | 30.40 | $1.75 | $14 | 73 |
| 118 | DeepSeek V4 Pro 0424 (Max) | DeepSeek | 30.40 | $0.435 | $0.87 | 84 |
| 119 | GPT-5.6 Terra (Medium) | OpenAI | 30.10 | $2 | $12 | 88 |
| 120 | Kimi K3 (Low) | Kimi | 30.10 | $3 | $15 | 43 |
| 121 | DeepSeek V4 Pro 0424 (High) | DeepSeek | 30.10 | $0.435 | $0.87 | 94 |
| 122 | Claude Sonnet 4.6 (Max) | Anthropic | 30.10 | $3 | $15 | 50 |
| 123 | GPT-6 Luna (Medium) | OpenAI | 29.90 | $0.1 | $0.5 | — |
| 124 | Gemini 3.1 Pro Preview | 29.70 | $2 | $12 | 131 | |
| 125 | Claude Haiku 5.5 (Low) | Anthropic | 29.50 | $0.1 | $0.5 | 146 |
| 126 | Qwen3.7 Max | Alibaba | 29.50 | $2.5 | $7.5 | 191 |
| 127 | MiniMax-M3 | MiniMax | 29.20 | $0.3 | $1.2 | 99 |
| 128 | Claude Opus 4.5 (Reasoning) | Anthropic | 29.10 | $5 | $25 | 48 |
| 129 | MiMo-V2-Pro | Xiaomi | 28.60 | — | — | — |
| 130 | GPT-5.2 Codex (Xhigh) | OpenAI | 28.50 | $1.75 | $14 | 115 |
| 131 | GPT-6 Sol (Non-reasoning) | OpenAI | 28.50 | $2 | $10 | 86 |
| 132 | Qwen3.6 Max Preview | Alibaba | 28.40 | — | — | — |
| 133 | GPT-5.6 Sol (Non-reasoning) | OpenAI | 28.30 | $4 | $20 | 74 |
| 134 | Solar Pro 4 | Upstage | 28.20 | $0.3 | $1.2 | 93 |
| 135 | Nex-N2-Pro (Based on Qwen3.5-397B-A17B) | Nex AGI | 28.20 | — | — | — |
| 136 | Claude Sonnet 5 (Medium) | Anthropic | 28.10 | $2 | $10 | 57 |
| 137 | Gemini 3 Pro Preview (High) | 28.00 | $2 | $12 | — | |
| 138 | GLM-5 (Reasoning) | Z AI | 27.90 | $1 | $3.2 | 71 |
| 139 | GPT-5.4 (Low) | OpenAI | 27.60 | $2.5 | $15 | 62 |
| 140 | Qwen3.8 27B (Medium) | Alibaba | 27.60 | $0.5 | $3 | 43 |
| 141 | GPT-5.6 Terra (Low) | OpenAI | 27.50 | $2 | $12 | 93 |
| 142 | JT-4.1 Flash 236B A21B (Non-reasoning) | China Mobile | 27.30 | — | — | — |
| 143 | Grok Build 0.1 0616 | SpaceXAI | 27.20 | $1 | $2 | 67 |
| 144 | Kimi K2.6 (Reasoning) | Kimi | 27.00 | $0.95 | $4 | 53 |
| 145 | Qwen3.6 Plus | Alibaba | 27.00 | $0.5 | $3 | 56 |
| 146 | Quasar 438B (Max, Based on GLM-5.2) | Multiverse Computing | 26.70 | $0.6 | $1.8 | 145 |
| 147 | GLM-5-Turbo | Z AI | 26.60 | — | — | — |
| 148 | GPT-5.2 (Medium) | OpenAI | 26.50 | $1.75 | $14 | — |
| 149 | Apodex 1.1 | Apodex | 26.40 | $0.3 | $3 | — |
| 150 | Claude Opus 4.6 (Non-reasoning, High) | Anthropic | 26.40 | $5 | $25 | 38 |
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.