| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | GPT-5.2 Pro gpt-5.2-pro-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 53.4 Agentic | 65.5 | 0.0 | 53.4 | 0.0 | 0.0 | N/A |
| 22 | Claude Haiku 4.5 claude-haiku-4-5-20251001 multimodalvisionmulti-input reasoning | Anthropic | 53.3 Agentic | 31.5 | 55.3 | 53.3 | 54.9 | 38.7 | |
| 23 | Kimi K2-Thinking-0905 kimi-k2-thinking-0905 codeprogrammingtool use | Moonshot AI | 52.8 Agentic | 68.7 | 0.0 | 52.8 | 59.8 | 0.0 | |
| 24 | MiniMax M2.1 minimax-m2.1 codeprogrammingtool use | MiniMax | 52.1 Agentic | 40.8 | 72.2 | 52.1 | 48.7 | 68.6 | $0.3 in / $1.2 out |
| 25 | Seed 2.0 Pro seed-2.0-pro multimodalvisionmulti-input reasoning | ByteDance | 51.9 Agentic | 68.0 | 0.0 | 51.9 | 58.5 | 0.0 | N/A |
| 26 | Qwen3-Coder 480B A35B Instruct qwen3-coder-480b-a35b-instruct codeprogrammingtool use | Alibaba Cloud / Qwen Team | 50.7 Agentic | 0.0 | 0.0 | 50.7 | 33.6 | 0.0 | |
| 27 | MiniMax M2.5 minimax-m2.5 codeprogrammingtool use | MiniMax | 50.4 Agentic | 0.0 | 72.2 | 50.4 | 56.9 | 68.6 | $0.3 in / $1.2 out |
| 28 | Claude Sonnet 4 claude-sonnet-4-20250514 multimodalvisionmulti-input reasoning | Anthropic | 49.4 Agentic | 39.9 | 0.0 | 49.4 | 43.6 | 0.0 | |
| 29 | Claude 3.7 Sonnet claude-3-7-sonnet-20250219 multimodalvisionmulti-input reasoning | Anthropic | 49.1 Agentic | 43.0 | 0.0 | 49.1 | 38.8 | 0.0 | |
| 30 | Qwen3.5-122B-A10B qwen3.5-122b-a10b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 48.7 Agentic | 63.6 | 41.1 | 48.7 | 39.5 | 43.0 | $0.4 in / $3.2 out |
| 31 | LongCat-Flash-Chat longcat-flash-chat codeprogrammingtool use | Meituan | 48.1 Agentic | 26.9 | 0.0 | 48.1 | 37.4 | 0.0 | N/A |
| 32 | Claude Sonnet 4.6 claude-sonnet-4-6 multimodalvisionmulti-input reasoning | Anthropic | 47.6 Agentic | 64.7 | 14.6 | 47.6 | 66.4 | 9.3 | |
| 33 | DeepSeek-V4-Flash-Max deepseek-v4-flash-max codeprogrammingtool use | DeepSeek | 47.6 Agentic | 58.3 | 89.2 | 47.6 | 44.2 | 98.7 | |
| 34 | Kimi K2.5 kimi-k2.5 multimodalvisionmulti-input reasoning | Moonshot AI | 47.3 Agentic | 67.2 | 0.0 | 47.3 | 44.6 | 0.0 | N/A |
| 35 | GLM-5.1 glm-5.1 codeprogrammingtool use | Zhipu AI | 46.0 Agentic | 66.3 | 21.5 | 46.0 | 54.9 | 31.6 | $1.4 in / $4.4 out |
| 36 | Qwen3.5-27B qwen3.5-27b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 44.9 Agentic | 60.8 | 41.1 | 44.9 | 40.3 | 53.2 | $0.3 in / $2.4 out |
| 37 | o1 o1-2024-12-17 multimodalvisionmulti-input reasoning | OpenAI | 44.7 Agentic | 42.3 | 0.0 | 44.7 | 6.0 | 0.0 | N/A |
| 38 | GPT-5.2 gpt-5.2-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 44.4 Agentic | 75.3 | 66.9 | 44.4 | 70.7 | 27.1 | |
| 39 | GLM-5 glm-5 codeprogrammingtool use | Zhipu AI | 43.6 Agentic | 0.0 | 8.7 | 43.6 | 62.5 | 31.8 | $1 in / $3.2 out |
| 40 | Qwen3.6 Plus qwen3.6-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 42.1 Agentic | 70.2 | 72.2 | 42.1 | 61.0 | 44.9 | $0.5 in / $3 out |
21
GPT-5.2 Pro
OpenAI
53.4
N/A
22
Claude Haiku 4.5
Anthropic
53.3
$1 in / $5 out
23
Kimi K2-Thinking-0905
Moonshot AI
52.8
N/A
24