| 1 | — | Oo3-pro閉源OpenAI | 71.0 | $35 | — | — |
| 2 | — | GGemini 2.5 Pro Preview (Jun '25)閉源Google | 70.5 | $3.4 | — | — |
| 3 | — | Oo3閉源OpenAI | 70.0 | $3.5 | — | — |
| 4 | — | Oo4-mini (high)閉源OpenAI | 69.8 | $1.9 | — | — |
| 5 | — | GGemini 2.5 Pro Preview (Mar' 25)閉源Google | 68.9 | $3.4 | — | — |
| 6 | — | GGemini 2.5 Pro Preview (May' 25)閉源Google | 67.9 | $3.4 | — | — |
| 7 | — | XGrok 3 mini Reasoning (high)閉源xAI | 66.7 | $0.35 | — | — |
| 8 | — | Oo3-mini (high)閉源OpenAI | 65.5 | $1.9 | — | — |
| 9 | — | GGemini 2.5 Flash Preview (May '25) (Reasoning)閉源Google | 65.1 | $0.99 | — | — |
| 10 | — | AClaude 4 Opus (Extended Thinking)閉源Anthropic | 64.4 | $30 | — | — |
| 11 | — | Oo3-mini閉源OpenAI | 62.9 | $1.9 | — | — |
| 12 | — | Oo1閉源OpenAI | 61.9 | $26 | — | — |
| 13 | — | NLlama 3.1 Nemotron Ultra 253B v1 (Reasoning)開源NVIDIA | 60.8 | $0.90 | — | — |
| 14 | — | AClaude 4 Sonnet (Extended Thinking)閉源Anthropic | 60.8 | $6.0 | — | — |
| 15 | — | GGemini 2.5 Flash Preview (Reasoning)閉源Google | 60.5 | $0.99 | — | — |
| 16 | — | Oo1-preview閉源OpenAI | 59.6 | $26 | — | — |
| 17 | — | AClaude 4 Opus閉源Anthropic | 57.7 | $30 | — | — |
| 18 | — | AClaude 3.7 Sonnet (Extended Thinking)閉源Anthropic | 57.4 | $6.0 | — | — |
| 19 | — | XGrok 3 Reasoning Beta閉源xAI | 56.1 | $0.000 | — | — |
| 19 | — | Oo1-pro閉源OpenAI | 56.1 | $263 | — | — |
| 21 | — | Oo1-mini閉源OpenAI | 53.8 | $1.9 | — | — |
| 22 | — | GGemini 2.5 Flash Preview (May '25)閉源Google | 53.4 | $0.26 | — | — |
| 23 | — | AClaude 4 Sonnet閉源Anthropic | 53.0 | $6.0 | — | — |
| 23 | — | OGPT-4.5 (Preview)閉源OpenAI | 53.0 | $94 | — | — |
| 25 | — | OGPT-4.1 mini閉源OpenAI | 52.9 | $0.70 | — | — |
| 26 | — | OGPT-4.1閉源OpenAI | 52.6 | $3.5 | — | — |
| 27 | — | GGemini 2.0 Flash Thinking Experimental (Jan '25)閉源Google | 52.3 | $0.000 | — | — |
| 28 | — | NLlama 3.3 Nemotron Super 49B v1 (Reasoning)開源NVIDIA | 51.2 | $0.000 | — | — |
| 29 | — | XGrok 3閉源xAI | 50.6 | $6.0 | — | — |
| 30 | — | MLlama 4 Maverick開源Meta | 50.5 | $0.38 | — | — |
| 31 | — | OGPT-4o (March 2025, chatgpt-4o-latest)閉源OpenAI | 50.3 | $7.5 | — | — |
| 32 | — | GGemini 2.0 Pro Experimental (Feb '25)閉源Google | 49.2 | $0.000 | — | — |
| 33 | — | PSonar Reasoning閉源Perplexity | 48.8 | $2.0 | — | — |
| 34 | — | GGemini 2.5 Flash Preview閉源Google | 48.8 | $0.26 | — | — |
| 35 | — | AClaude 3.7 Sonnet (Standard)閉源Anthropic | 48.2 | $6.0 | — | — |
| 36 | — | GGemini 2.0 Flash (Feb '25)閉源Google | 48.1 | $0.18 | — | — |
| 37 | — | GGemini 2.0 Flash (experimental)閉源Google | 46.4 | $0.000 | — | — |
| 38 | — | NLlama 3.1 Nemotron Nano 4B v1.1 (Reasoning)開源NVIDIA | 45.0 | $0.000 | — | — |
| 39 | — | GGemini 1.5 Pro (Sep '24)閉源Google | 44.6 | $2.2 | — | — |
| 40 | — | AClaude 3.5 Sonnet (Oct '24)閉源Anthropic | 44.4 | $6.0 | — | — |
| 41 | — | PSonar閉源Perplexity | 43.4 | $1.0 | — | — |
| 42 | — | MLlama 4 Scout開源Meta | 43.0 | $0.24 | — | — |
| 43 | — | PSonar Pro閉源Perplexity | 42.7 | $6.0 | — | — |
| 44 | — | ANova Premier閉源Amazon | 42.6 | $5.0 | — | — |
| 45 | — | OGPT-4o (Nov '24)閉源OpenAI | 41.5 | $4.4 | — | — |
| 46 | — | GGemini 2.0 Flash-Lite (Feb '25)閉源Google | 41.4 | $0.13 | — | — |
| 47 | — | MLlama 3.3 Instruct 70B開源Meta | 41.1 | $0.62 | — | — |
| 48 | — | OGPT-4.1 nano閉源OpenAI | 41.0 | $0.18 | — | — |
| 49 | — | OGPT-4o (May '24)閉源OpenAI | 40.9 | $7.5 | — | — |
| 50 | — | GGemini 2.0 Flash-Lite (Preview)閉源Google | 40.8 | $0.13 | — | — |
| 51 | — | OGPT-4o (Aug '24)閉源OpenAI | 40.5 | $4.4 | — | — |
| 52 | — | MLlama 3.1 Instruct 405B開源Meta | 40.5 | $3.5 | — | — |
| 53 | — | MPhi-4開源Microsoft Azure | 40.2 | $0.22 | — | — |
| 54 | — | AClaude 3.5 Sonnet (June '24)閉源Anthropic | 40.0 | $6.0 | — | — |
| 55 | — | OGPT-4o (ChatGPT)閉源OpenAI | 39.8 | $7.5 | — | — |
| 56 | — | NLlama 3.3 Nemotron Super 49B v1開源NVIDIA | 39.3 | $0.000 | — | — |
| 57 | — | XGrok 2 (Dec '24)閉源xAI | 39.2 | $0.000 | — | — |
| 58 | — | GGemini 1.5 Flash (Sep '24)閉源Google | 39.0 | $0.13 | — | — |
| 59 | — | OGPT-4 Turbo閉源OpenAI | 38.8 | $15 | — | — |
| 60 | — | GGemma 3 27B Instruct開源Google | 37.6 | $0.000 | — | — |
| 61 | — | XGrok Beta閉源xAI | 37.5 | $7.5 | — | — |
| 62 | — | NLlama 3.1 Nemotron Instruct 70B開源NVIDIA | 37.3 | $0.16 | — | — |
| 63 | — | ANova Pro閉源Amazon | 37.1 | $1.4 | — | — |
| 64 | — | OGPT-4閉源OpenAI | 36.0 | $38 | — | — |
| 65 | — | OGPT-4o mini閉源OpenAI | 35.7 | $0.26 | — | — |
| 66 | — | MLlama 3.1 Instruct 70B開源Meta | 35.4 | $0.72 | — | — |
| 67 | — | AClaude 3 Opus閉源Anthropic | 35.1 | $30 | — | — |
| 68 | — | AClaude 3.5 Haiku閉源Anthropic | 34.7 | $1.6 | — | — |
| 69 | — | GGemini 2.0 Flash Thinking Experimental (Dec '24)閉源Google | 34.7 | $0.000 | — | — |
| 70 | — | GGemma 3 12B Instruct開源Google | 33.8 | $0.063 | — | — |
| 71 | — | GGemini 1.5 Pro (May '24)閉源Google | 33.7 | $2.2 | — | — |
| 72 | — | PR1 1776開源Perplexity | 33.7 | $3.5 | — | — |
| 73 | — | GGemma 3 1B Instruct開源Google | 33.4 | $0.000 | — | — |
| 74 | — | MLlama 3.2 Instruct 90B (Vision)開源Meta | 33.4 | $0.72 | — | — |
| 75 | — | ANova Lite閉源Amazon | 32.5 | $0.11 | — | — |
| 76 | — | GGemini 1.5 Flash-8B閉源Google | 30.8 | $0.066 | — | — |
| 77 | — | GGemini 1.5 Flash (May '24)閉源Google | 28.5 | $0.13 | — | — |
| 78 | — | ANova Micro閉源Amazon | 28.3 | $0.061 | — | — |
| 79 | — | AClaude 3 Sonnet閉源Anthropic | 27.8 | $6.0 | — | — |
| 80 | — | MLlama 3 Instruct 70B開源Meta | 27.5 | $0.75 | — | — |
| 81 | — | GGemini 1.0 Ultra閉源Google | 27.3 | $0.000 | — | — |
| 82 | — | MPhi-4 Multimodal Instruct開源Microsoft Azure | 26.9 | $0.000 | — | — |
| 83 | — | MPhi-4 Mini Instruct開源Microsoft Azure | 26.0 | $0.000 | — | — |
| 84 | — | GGemma 2 27B開源Google | 25.6 | $0.80 | — | — |
| 85 | — | MLlama 3.2 Instruct 11B (Vision)開源Meta | 25.0 | $0.16 | — | — |
| 86 | — | MPhi-3 Medium Instruct 14B開源Microsoft Azure | 24.5 | $0.30 | — | — |
| 87 | — | GGemma 3 4B Instruct開源Google | 24.5 | $0.025 | — | — |
| 88 | — | AClaude 2.1閉源Anthropic | 24.1 | $12 | — | — |
| 89 | — | AClaude 3 Haiku閉源Anthropic | 24.0 | $0.50 | — | — |
| 90 | — | MLlama 3.1 Instruct 8B開源Meta | 23.7 | $0.10 | — | — |
| 91 | — | AClaude 2.0閉源Anthropic | 23.0 | $12 | — | — |
| 92 | — | OGPT-3.5 Turbo閉源OpenAI | 22.7 | $0.75 | — | — |
| 93 | — | GGemma 2 9B開源Google | 22.2 | $0.12 | — | — |
| 94 | — | MPhi-3 Mini Instruct 3.8B開源Microsoft Azure | 22.1 | $0.000 | — | — |
| 95 | — | SArctic Instruct開源Snowflake | 22.0 | $0.000 | — | — |
| 96 | — | LLFM 40B閉源Liquid AI | 21.7 | $0.15 | — | — |
| 97 | — | MLlama 3 Instruct 8B開源Meta | 21.5 | $0.080 | — | — |
| 98 | — | GPALM-2閉源Google | 21.0 | $0.000 | — | — |
| 99 | — | GGemini 1.0 Pro閉源Google | 20.6 | $0.75 | — | — |
| 100 | — | MLlama 2 Chat 70B開源Meta | 20.0 | $0.000 | — | — |
| 101 | — | MLlama 2 Chat 13B開源Meta | 19.9 | $0.000 | — | — |
| 102 | — | DDBRX Instruct開源Databricks | 19.8 | $0.000 | — | — |
| 103 | — | MLlama 3.2 Instruct 3B開源Meta | 19.5 | $0.048 | — | — |
| 104 | — | AClaude Instant閉源Anthropic | 14.0 | $1.2 | — | — |
| 105 | — | MLlama 65B開源Meta | 11.0 | $0.000 | — | — |
| 106 | — | MLlama 3.2 Instruct 1B開源Meta | 9.7 | $0.050 | — | — |
| 107 | — | MLlama 2 Chat 7B開源Meta | 8.3 | $0.10 | — | — |