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 · 101–150
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 101 | Gemini 3 Flash Preview (Reasoning) | 38.70 | $0.5 | $3 | 177 | |
| 102 | Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 38.30 | $0.6 | $2.75 | 152 |
| 103 | MiMo-V2.5 | Xiaomi | 38.00 | $0.14 | $0.28 | 65 |
| 104 | Grok 4.20 0309 v2 (Reasoning) | SpaceXAI | 38.00 | $1.25 | $2.5 | 106 |
| 105 | Grok 4.3 (high) | SpaceXAI | 37.90 | $1.25 | $2.5 | 130 |
| 106 | Ling 3.0 Flash | InclusionAI | 37.80 | $0.07 | $0.22 | 385 |
| 107 | Qwen3.6 27B (Reasoning) | Alibaba | 37.70 | $0.6 | $3.6 | 50 |
| 108 | GPT-5.1 (high) | OpenAI | 37.50 | $1.25 | $10 | 104 |
| 109 | Grok 4.20 0309 (Reasoning) | SpaceXAI | 37.40 | $2 | $6 | — |
| 110 | Gemini 3.5 Flash-Lite | 37.40 | $0.3 | $2.5 | 379 | |
| 111 | Solar Open2 250B | Upstage | 37.40 | — | — | — |
| 112 | Claude 4.5 Sonnet (Reasoning) | Anthropic | 37.40 | $3 | $15 | 50 |
| 113 | MiMo-V2-Omni-0327 | Xiaomi | 37.30 | — | — | — |
| 114 | GPT-5 Codex (high) | OpenAI | 37.00 | $1.25 | $10 | — |
| 115 | Grok 4.3 (medium) | SpaceXAI | 36.90 | $1.25 | $2.5 | 111 |
| 116 | Claude Sonnet 4.6 (Non-reasoning, High Effort) | Anthropic | 36.80 | $3 | $15 | 42 |
| 117 | GLM-5.1 (Non-reasoning) | Z AI | 36.30 | $1.39 | $4.4 | 55 |
| 118 | Grok 4.3 (low) | SpaceXAI | 36.30 | $1.25 | $2.5 | 113 |
| 119 | Kimi K2.5 (Reasoning) | Kimi | 36.00 | $0.6 | $3 | 65 |
| 120 | MiMo-V2-Omni | Xiaomi | 35.90 | — | — | — |
| 121 | Gemini 3.5 Flash (minimal) | 35.80 | $1.5 | $9 | 202 | |
| 122 | GPT-5.5 (Non-reasoning) | OpenAI | 35.80 | $5 | $30 | 75 |
| 123 | GPT-5.1 Codex (high) | OpenAI | 35.60 | $1.25 | $10 | — |
| 124 | Claude Opus 4.5 (Non-reasoning) | Anthropic | 35.60 | $5 | $25 | 45 |
| 125 | Kimi K2.6 (Non-reasoning) | Kimi | 35.40 | $0.95 | $4 | 36 |
| 126 | GLM 5V Turbo (Reasoning) | Z AI | 35.30 | — | — | — |
| 127 | GPT-5 (high) | OpenAI | 35.30 | $1.25 | $10 | 103 |
| 128 | Muse Glimmer (high) | Meta | 35.10 | $0.32 | $1.35 | 103 |
| 129 | Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic | 35.10 | $3 | $15 | 47 |
| 130 | A.X-K2 | SK Telecom | 35.00 | — | — | — |
| 131 | GLM-5.2 (Non-reasoning) | Z AI | 34.80 | $1.4 | $4.4 | 96 |
| 132 | Qwen3.8 27B (Non-reasoning) | Alibaba | 34.70 | $0.5 | $3 | 51 |
| 133 | Qwen3.5 27B (Reasoning) | Alibaba | 34.60 | $0.3 | $2.4 | 76 |
| 134 | GPT-5 (medium) | OpenAI | 34.60 | $1.25 | $10 | 96 |
| 135 | GPT-5.6 Terra (Non-reasoning) | OpenAI | 34.60 | $2 | $12 | 97 |
| 136 | MiniMax-M2.5 | MiniMax | 34.50 | $0.3 | $1.2 | 100 |
| 137 | GLM-4.7 (Reasoning) | Z AI | 34.50 | $0.6 | $2.2 | 77 |
| 138 | Claude 4.1 Opus (Reasoning) | Anthropic | 34.50 | $15 | $75 | — |
| 139 | Hy3-preview (Reasoning) | Tencent | 34.40 | $0.06 | $0.21 | — |
| 140 | Qwen3.5 397B A17B (Reasoning) | Alibaba | 34.30 | $0.6 | $3.6 | 80 |
| 141 | GPT-5.5 Instant (May 2026) | OpenAI | 34.30 | $5 | $30 | — |
| 142 | Grok 4 | SpaceXAI | 34.10 | $3 | $15 | — |
| 143 | MiMo-V2-Flash (Feb 2026) | Xiaomi | 34.00 | — | — | — |
| 144 | LongCat 2.0 | LongCat | 34.00 | $0.75 | $2.95 | 41 |
| 145 | G9v3-39A5B | AI9Stars | 34.00 | $0 | $0 | — |
| 146 | GPT-5.6 Luna (low) | OpenAI | 33.90 | $0.2 | $1.2 | 109 |
| 147 | Gemini 3 Pro Preview (low) | 33.90 | $2 | $12 | — | |
| 148 | KAT Coder Pro V2 | KwaiKAT | 33.70 | $0.3 | $1.2 | 100 |
| 149 | Kimi K2 Thinking | Kimi | 33.50 | $0.6 | $2.5 | 129 |
| 150 | o3-pro | OpenAI | 33.30 | $20 | $80 | — |
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.