| 1 | — | OGPT-5 (high)闭源OpenAI | 69.0 | $3.4 | — | — |
| 2 | — | OGPT-5 (medium)闭源OpenAI | 67.5 | $3.4 | — | — |
| 3 | — | XGrok 4闭源xAI | 67.5 | $6.0 | — | — |
| 4 | — | Oo3-pro闭源OpenAI | 67.5 | $35 | — | — |
| 5 | — | Oo3闭源OpenAI | 67.1 | $3.5 | — | — |
| 6 | — | OGPT-5 mini (high)闭源OpenAI | 65.4 | $0.69 | — | — |
| 7 | — | Oo4-mini (high)闭源OpenAI | 65.1 | $1.9 | — | — |
| 8 | — | GGemini 2.5 Pro闭源Google | 64.6 | $3.4 | — | — |
| 9 | — | OGPT-5 mini (medium)闭源OpenAI | 63.7 | $0.69 | — | — |
| 10 | — | OGPT-5 (low)闭源OpenAI | 63.4 | $3.4 | — | — |
| 11 | — | Ogpt-oss-120B开源OpenAI | 61.3 | $0.26 | — | — |
| 12 | — | AClaude 4.1 Opus (Extended Thinking)闭源Anthropic | 61.0 | $30 | — | — |
| 13 | — | GGemini 2.5 Pro Preview (Mar' 25)闭源Google | 59.0 | $3.4 | — | — |
| 14 | — | AClaude 4 Sonnet (Extended Thinking)闭源Anthropic | 58.8 | $6.0 | — | — |
| 15 | — | GGemini 2.5 Flash (Reasoning)闭源Google | 58.4 | $0.85 | — | — |
| 16 | — | XGrok 3 mini Reasoning (high)闭源xAI | 58.0 | $0.35 | — | — |
| 17 | — | GGemini 2.5 Pro Preview (May' 25)闭源Google | 58.0 | $3.4 | — | — |
| 18 | — | Oo3-mini (high)闭源OpenAI | 55.5 | $1.9 | — | — |
| 19 | — | AClaude 4 Opus (Extended Thinking)闭源Anthropic | 55.3 | $30 | — | — |
| 20 | — | OGPT-5 nano (high)闭源OpenAI | 54.7 | $0.14 | — | — |
| 21 | — | OGPT-5 nano (medium)闭源OpenAI | 53.8 | $0.14 | — | — |
| 22 | — | Oo3-mini闭源OpenAI | 52.7 | $1.9 | — | — |
| 23 | — | NLlama Nemotron Super 49B v1.5 (Reasoning)开源NVIDIA | 52.4 | $0.000 | — | — |
| 24 | — | Oo1闭源OpenAI | 51.7 | $26 | — | — |
| 25 | — | PSonar Reasoning Pro闭源Perplexity | 50.7 | $0.000 | — | — |
| 26 | — | GGemini 2.5 Flash Preview (Reasoning)闭源Google | 50.2 | $0.99 | — | — |
| 27 | — | Oo1-preview闭源OpenAI | 49.3 | $29 | — | — |
| 28 | — | Ogpt-oss-20B开源OpenAI | 49.0 | $0.088 | — | — |
| 29 | — | AClaude 4.1 Opus闭源Anthropic | 49.0 | $30 | — | — |
| 30 | — | GGemini 2.5 Flash闭源Google | 47.3 | $0.85 | — | — |
| 31 | — | GGemini 2.5 Flash-Lite (Reasoning)闭源Google | 47.3 | $0.18 | — | — |
| 32 | — | AClaude 3.7 Sonnet (Extended Thinking)闭源Anthropic | 47.0 | $6.0 | — | — |
| 33 | — | OGPT-4.1闭源OpenAI | 46.8 | $3.5 | — | — |
| 34 | — | AClaude 4 Opus闭源Anthropic | 46.6 | $30 | — | — |
| 35 | — | NLlama 3.1 Nemotron Ultra 253B v1 (Reasoning)开源NVIDIA | 46.4 | $0.90 | — | — |
| 36 | — | OGPT-5 mini (minimal)闭源OpenAI | 46.3 | $0.69 | — | — |
| 37 | — | AClaude 4 Sonnet闭源Anthropic | 45.7 | $6.0 | — | — |
| 38 | — | XGrok 3 Reasoning Beta闭源xAI | 45.6 | $0.000 | — | — |
| 38 | — | Oo1-pro闭源OpenAI | 45.6 | $263 | — | — |
| 40 | — | OGPT-4.1 mini闭源OpenAI | 45.6 | $0.70 | — | — |
| 41 | — | OGPT-5 (minimal)闭源OpenAI | 43.8 | $3.4 | — | — |
| 42 | — | Oo1-mini闭源OpenAI | 43.3 | $1.9 | — | — |
| 43 | — | NNVIDIA Nemotron Nano 9B V2 (Reasoning)开源NVIDIA | 43.2 | $0.000 | — | — |
| 44 | — | OGPT-4.5 (Preview)闭源OpenAI | 42.4 | $0.000 | — | — |
| 45 | 新 | NNVIDIA Nemotron Nano 9B V2开源NVIDIA | 42.1 | $0.000 | — | — |
| 46 | ▼ 1 | MLlama 4 Maverick开源Meta | 41.7 | $0.39 | — | — |
| 47 | ▼ 1 | GGemini 2.0 Flash Thinking Experimental (Jan '25)闭源Google | 41.7 | $0.000 | — | — |
| 48 | ▼ 1 | XGrok 3闭源xAI | 39.9 | $6.0 | — | — |
| 49 | ▼ 1 | OGPT-4o (March 2025, chatgpt-4o-latest)闭源OpenAI | 39.5 | $7.5 | — | — |
| 50 | ▼ 1 | NLlama 3.3 Nemotron Super 49B v1 (Reasoning)开源NVIDIA | 39.4 | $0.000 | — | — |
| 51 | ▼ 1 | GGemini 2.0 Pro Experimental (Feb '25)闭源Google | 38.4 | $0.000 | — | — |
| 52 | ▼ 1 | PSonar Reasoning闭源Perplexity | 38.0 | $2.0 | — | — |
| 53 | ▼ 1 | GGemini 2.5 Flash Preview闭源Google | 38.0 | $0.26 | — | — |
| 54 | ▼ 1 | GGemini 2.0 Flash (Feb '25)闭源Google | 37.8 | $0.18 | — | — |
| 55 | ▼ 1 | AClaude 3.7 Sonnet (Standard)闭源Anthropic | 37.3 | $6.0 | — | — |
| 56 | ▼ 1 | GGemini 2.0 Flash (experimental)闭源Google | 35.5 | $0.000 | — | — |
| 57 | ▼ 1 | GGemini 2.5 Flash-Lite闭源Google | 34.9 | $0.18 | — | — |
| 58 | ▼ 1 | ANova Premier闭源Amazon | 34.8 | $5.0 | — | — |
| 59 | — | GGemini 1.5 Pro (Sep '24)闭源Google | 33.6 | $0.000 | — | — |
| 60 | — | AClaude 3.5 Sonnet (Oct '24)闭源Anthropic | 33.5 | $6.0 | — | — |
| 61 | — | MLlama 4 Scout开源Meta | 33.1 | $0.23 | — | — |
| 62 | — | PSonar闭源Perplexity | 32.4 | $1.0 | — | — |
| 63 | — | OGPT-5 nano (minimal)闭源OpenAI | 32.3 | $0.14 | — | — |
| 64 | — | PSonar Pro闭源Perplexity | 31.7 | $6.0 | — | — |
| 65 | — | OGPT-4.1 nano闭源OpenAI | 31.6 | $0.18 | — | — |
| 66 | — | MLlama 3.3 Instruct 70B开源Meta | 31.2 | $0.57 | — | — |
| 67 | — | GGemini 2.0 Flash-Lite (Feb '25)闭源Google | 30.3 | $0.13 | — | — |
| 68 | — | OGPT-4o (May '24)闭源OpenAI | 29.7 | $7.5 | — | — |
| 69 | — | GGemini 2.0 Flash-Lite (Preview)闭源Google | 29.7 | $0.13 | — | — |
| 70 | — | NLlama Nemotron Super 49B v1.5开源NVIDIA | 29.7 | $0.000 | — | — |
| 71 | — | OGPT-4o (Nov '24)闭源OpenAI | 29.6 | $4.4 | — | — |
| 72 | ▼ 14 | NLlama 3.1 Nemotron Nano 4B v1.1 (Reasoning)开源NVIDIA | 29.6 | $0.000 | — | — |
| 73 | ▼ 1 | OGPT-4o (Aug '24)闭源OpenAI | 29.4 | $4.4 | — | — |
| 74 | ▼ 1 | NLlama 3.3 Nemotron Super 49B v1开源NVIDIA | 29.3 | $0.000 | — | — |
| 75 | ▼ 1 | MLlama 3.1 Instruct 405B开源Meta | 28.9 | $3.5 | — | — |
| 76 | ▼ 1 | ANova Pro闭源Amazon | 28.8 | $1.4 | — | — |
| 77 | ▼ 1 | AClaude 3.5 Sonnet (June '24)闭源Anthropic | 28.8 | $6.0 | — | — |
| 78 | ▼ 1 | OGPT-4o (ChatGPT)闭源OpenAI | 28.6 | $7.5 | — | — |
| 79 | ▼ 1 | XGrok 2 (Dec '24)开源xAI | 28.0 | $0.000 | — | — |
| 80 | ▼ 1 | MPhi-4开源Microsoft Azure | 28.0 | $0.22 | — | — |
| 81 | ▼ 1 | GGemini 1.5 Flash (Sep '24)闭源Google | 27.7 | $0.000 | — | — |
| 82 | ▼ 1 | OGPT-4 Turbo闭源OpenAI | 27.5 | $15 | — | — |
| 83 | ▼ 1 | XGrok Beta闭源xAI | 26.3 | $0.000 | — | — |
| 84 | ▼ 1 | NLlama 3.1 Nemotron Instruct 70B开源NVIDIA | 26.1 | $0.16 | — | — |
| 85 | ▼ 1 | MLlama 3.1 Instruct 70B开源Meta | 26.0 | $0.76 | — | — |
| 86 | ▼ 1 | GGemma 3 27B Instruct开源Google | 25.2 | $0.000 | — | — |
| 87 | ▼ 1 | OGPT-4闭源OpenAI | 24.6 | $38 | — | — |
| 88 | ▼ 1 | ANova Lite闭源Amazon | 24.5 | $0.11 | — | — |
| 89 | ▼ 1 | OGPT-4o mini闭源OpenAI | 24.3 | $0.26 | — | — |
| 90 | ▼ 1 | GGemma 3 12B Instruct开源Google | 24.0 | $0.23 | — | — |
| 91 | ▼ 1 | AClaude 3 Opus闭源Anthropic | 23.7 | $30 | — | — |
| 92 | ▼ 1 | AClaude 3.5 Haiku闭源Anthropic | 23.3 | $1.6 | — | — |
| 93 | ▼ 1 | GGemini 2.0 Flash Thinking Experimental (Dec '24)闭源Google | 23.3 | $0.000 | — | — |
| 94 | ▼ 1 | GGemini 1.5 Pro (May '24)闭源Google | 22.2 | $0.000 | — | — |
| 95 | ▼ 1 | PR1 1776开源Perplexity | 22.2 | $3.5 | — | — |
| 96 | ▼ 1 | MLlama 3.2 Instruct 90B (Vision)开源Meta | 21.9 | $0.72 | — | — |
| 97 | ▼ 1 | XGrok-1开源xAI | 21.2 | $0.000 | — | — |
| 98 | ▼ 1 | ANova Micro闭源Amazon | 20.2 | $0.061 | — | — |
| 99 | ▼ 1 | GGemma 2 27B开源Google | 20.1 | $0.80 | — | — |
| 100 | ▼ 1 | GGemini 1.5 Flash-8B闭源Google | 19.2 | $0.000 | — | — |
| 101 | ▼ 1 | MLlama 3.1 Instruct 8B开源Meta | 19.0 | $0.10 | — | — |
| 102 | ▼ 1 | MPhi-4 Mini Instruct开源Microsoft Azure | 18.6 | $0.000 | — | — |
| 103 | ▼ 1 | GGemma 3n E4B Instruct开源Google | 18.5 | $0.025 | — | — |
| 104 | ▼ 1 | GGemma 3 4B Instruct开源Google | 17.6 | $0.025 | — | — |
| 105 | ▼ 1 | IGranite 3.3 Instruct 8B开源IBM | 17.6 | $0.085 | — | — |
| 106 | ▼ 1 | MLlama 3.2 Instruct 11B (Vision)开源Meta | 17.5 | $0.16 | — | — |
| 107 | ▼ 1 | GGemini 1.5 Flash (May '24)闭源Google | 16.8 | $0.000 | — | — |
| 108 | ▼ 1 | AClaude 3 Sonnet闭源Anthropic | 16.0 | $6.0 | — | — |
| 109 | ▼ 1 | MPhi-3 Mini Instruct 3.8B开源Microsoft Azure | 15.8 | $0.23 | — | — |
| 110 | ▼ 1 | MLlama 3 Instruct 70B开源Meta | 15.7 | $0.75 | — | — |
| 111 | ▼ 1 | GGemini 1.0 Ultra闭源Google | 15.6 | $0.000 | — | — |
| 112 | ▼ 1 | GGemma 3n E4B Instruct Preview (May '25)开源Google | 15.2 | $0.000 | — | — |
| 113 | ▼ 1 | MPhi-4 Multimodal Instruct开源Microsoft Azure | 15.1 | $0.000 | — | — |
| 114 | ▼ 1 | MLlama 2 Chat 7B开源Meta | 13.9 | $0.10 | — | — |
| 115 | ▼ 1 | MLlama 3.2 Instruct 3B开源Meta | 13.8 | $0.035 | — | — |
| 116 | ▼ 1 | MPhi-3 Medium Instruct 14B开源Microsoft Azure | 12.7 | $0.30 | — | — |
| 117 | ▼ 1 | AClaude 2.1闭源Anthropic | 12.2 | $12 | — | — |
| 118 | ▼ 1 | AClaude 3 Haiku闭源Anthropic | 12.1 | $0.50 | — | — |
| 119 | ▼ 1 | AClaude 2.0闭源Anthropic | 11.1 | $0.000 | — | — |
| 120 | ▼ 1 | OGPT-3.5 Turbo闭源OpenAI | 10.8 | $0.75 | — | — |
| 121 | ▼ 1 | LLFM2 1.2B开源Liquid AI | 10.5 | $0.000 | — | — |
| 122 | ▼ 1 | GGemma 3n E2B Instruct开源Google | 10.4 | $0.000 | — | — |
| 123 | ▼ 1 | GGemma 2 9B开源Google | 10.2 | $0.20 | — | — |
| 124 | ▼ 1 | SArctic Instruct开源Snowflake | 10.0 | $0.000 | — | — |
| 125 | ▼ 1 | LLFM 40B闭源Liquid AI | 9.7 | $0.15 | — | — |
| 126 | ▼ 1 | MLlama 3.2 Instruct 1B开源Meta | 9.5 | $0.053 | — | — |
| 127 | ▼ 1 | MLlama 3 Instruct 8B开源Meta | 9.5 | $0.058 | — | — |
| 128 | ▼ 1 | GPALM-2闭源Google | 9.0 | $0.000 | — | — |
| 129 | ▼ 1 | GGemini 1.0 Pro闭源Google | 8.5 | $0.75 | — | — |
| 130 | ▼ 1 | GGemma 3 1B Instruct开源Google | 8.5 | $0.000 | — | — |
| 131 | ▼ 1 | MLlama 2 Chat 70B开源Meta | 7.9 | $0.000 | — | — |
| 132 | ▼ 1 | MLlama 2 Chat 13B开源Meta | 7.9 | $0.000 | — | — |
| 133 | ▼ 1 | DDBRX Instruct开源Databricks | 7.7 | $0.000 | — | — |
| 134 | ▼ 1 | AClaude Instant闭源Anthropic | 1.7 | $1.2 | — | — |
| 135 | ▼ 1 | MLlama 65B开源Meta | 1.0 | $0.000 | — | — |