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 · 51–100
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 51 | GPT-5.6 Terra (Max) | OpenAI | 42.10 | $2 | $12 | 107 |
| 52 | GPT-6.1 Sol (Low) | OpenAI | 42.10 | $2 | $10 | 44 |
| 53 | GLM-5.3-Flash | Z AI | 41.80 | $0.15 | $0.5 | 62 |
| 54 | Claude Opus 4.8 (Max) | Anthropic | 41.80 | $5 | $25 | 58 |
| 55 | Claude Haiku 5.5 (Xhigh) | Anthropic | 41.20 | $0.1 | $0.5 | 181 |
| 56 | Ling 3.1 Flash | InclusionAI | 41.10 | $0.3 | $0.9 | 211 |
| 57 | Gemini 3.8 Flash (High) | 40.90 | $0.75 | $3.75 | 140 | |
| 58 | Claude Sonnet 5.5 (Medium, Default Fallback) | Anthropic | 40.80 | $2 | $10 | 95 |
| 59 | Claude Opus 4.7 (Max) | Anthropic | 40.70 | $5 | $25 | 53 |
| 60 | Qwen3.8 Max | Alibaba | 40.20 | $2 | $6 | 39 |
| 61 | Qwen3.8 2.4T A95B | Alibaba | 39.90 | $2 | $6 | 39 |
| 62 | Gemini 3.8 Flash (Medium) | 39.80 | $0.75 | $3.75 | — | |
| 63 | GPT-6 Sol (Medium) | OpenAI | 39.80 | $2 | $10 | — |
| 64 | Qwen3.8-Flash-Next | Alibaba | 39.80 | $0.15 | $0.47 | 52 |
| 65 | Muse Spark 1.2 (Xhigh) | Meta | 39.60 | $1.25 | $4.25 | 322 |
| 66 | Gemini 3.7 Flash (Medium) | 39.60 | $0.75 | $3.75 | 290 | |
| 67 | DeepSeek V4.1 Flash (Max) | DeepSeek | 39.50 | $0.3 | $1.2 | 174 |
| 68 | Claude Opus 5 (Low) | Anthropic | 39.40 | $5 | $25 | 50 |
| 69 | GPT-5.6 Sol (Medium) | OpenAI | 39.20 | $4 | $20 | 77 |
| 70 | Gemini 3.7 Flash (High) | 39.10 | $0.75 | $3.75 | 297 | |
| 71 | GPT-5.4 (Xhigh) | OpenAI | 39.00 | $2.5 | $15 | 85 |
| 72 | Grok 4.5 (High) | SpaceXAI | 38.80 | $2 | $6 | 57 |
| 73 | GPT-5.5 (Xhigh) | OpenAI | 38.40 | $5 | $30 | 82 |
| 74 | Mistral Large 4 Preview | Mistral | 38.40 | $1.36 | $4.18 | — |
| 75 | Claude Sonnet 5 (Max) | Anthropic | 38.20 | $2 | $10 | 75 |
| 76 | GPT-6 Luna (Max) | OpenAI | 38.10 | $0.1 | $0.5 | 117 |
| 77 | GPT-5.6 Terra (Xhigh) | OpenAI | 38.00 | $2 | $12 | 98 |
| 78 | MiMo-V2.6-Flash | Xiaomi | 37.90 | $0.14 | $0.28 | 54 |
| 79 | Claude Haiku 5.5 (High) | Anthropic | 37.80 | $0.1 | $0.5 | 157 |
| 80 | GPT-5.6 Luna (Max) | OpenAI | 37.30 | $0.2 | $1.2 | 115 |
| 81 | GPT-5.5 (High) | OpenAI | 37.00 | $5 | $30 | 83 |
| 82 | Gemini 3.7 Flash (Low) | 36.90 | $0.75 | $3.75 | 302 | |
| 83 | DeepSeek V4 Pro 0813 (Max) | DeepSeek | 36.00 | $1.32 | $3.96 | 92 |
| 84 | Claude Sonnet 5.5 (Low, Default Fallback) | Anthropic | 35.90 | $2 | $10 | 92 |
| 85 | Agnes 2.5 Pro Beta | Sapiens AI | 35.20 | $0.1 | $0.3 | 119 |
| 86 | Grok 4.6 (Low) | SpaceXAI | 35.10 | $2 | $6 | 51 |
| 87 | DeepSeek V4 Flash Vision (Max) | DeepSeek | 34.80 | $0.44 | $1.32 | 173 |
| 88 | GPT-6 Luna (Xhigh) | OpenAI | 34.60 | $0.1 | $0.5 | 111 |
| 89 | GPT-5.6 Luna (Xhigh) | OpenAI | 34.60 | $0.2 | $1.2 | 120 |
| 90 | Claude Haiku 5.5 (Medium) | Anthropic | 34.50 | $0.1 | $0.5 | 144 |
| 91 | Claude Sonnet 5 (Xhigh) | Anthropic | 34.40 | $2 | $10 | 62 |
| 92 | GLM-5.3 (Low) | Z AI | 34.30 | $1.4 | $4.4 | 70 |
| 93 | DeepSeek V4 Flash 0731 (Max) | DeepSeek | 34.30 | $0.44 | $1.32 | 173 |
| 94 | GPT-6 Sol (Low) | OpenAI | 34.20 | $2 | $10 | 86 |
| 95 | GPT-5.6 Terra (High) | OpenAI | 34.20 | $2 | $12 | 93 |
| 96 | Gemini 3.6 Flash (High) | 34.00 | $0.75 | $3.75 | 175 | |
| 97 | JT-4.1 Flash 236B A21B (Reasoning) | China Mobile | 33.90 | — | — | — |
| 98 | GPT-5.5 (Medium) | OpenAI | 33.80 | $5 | $30 | 82 |
| 99 | Qwen3.8 27B (Xhigh) | Alibaba | 33.70 | $0.5 | $3 | 41 |
| 100 | Muse Spark 1.1 (Xhigh) | Meta | 33.70 | $1.25 | $4.25 | 148 |
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.