| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 41 | Claude Sonnet 4 claude-sonnet-4-20250514 multimodalvisionmulti-input reasoning | Anthropic | 49.4 Agentic | 38.3 | 0.0 | 49.4 | 42.8 | 0.0 | N/A |
| 42 | Qwen3 VL 235B A22B Instruct qwen3-vl-235b-a22b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 49.3 Agentic | 32.6 | 41.8 | 49.3 | 0.0 | 65.4 | |
| 43 | Claude 3.7 Sonnet claude-3-7-sonnet-20250219 multimodalvisionmulti-input reasoning | Anthropic | 49.1 Agentic | 41.2 | 0.0 | 49.1 | 36.6 | 0.0 | |
| 44 | Qwen3.7 Max qwen3.7-max multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 48.6 Agentic | 64.4 | 66.7 | 48.6 | 72.6 | 30.5 | $1.25 in / $3.75 out |
| 45 | Nemotron 3.5 Super VL (120B A12B) nemotron-3.5-super-vl-120b-a12b multimodalvisionmulti-input reasoning | NVIDIA | 48.2 Agentic | 52.2 | 41.8 | 48.2 | 35.3 | 62.9 | |
| 46 | LongCat-Flash-Chat longcat-flash-chat codeprogrammingtool use | Meituan | 48.1 Agentic | 24.8 | 0.0 | 48.1 | 36.6 | 0.0 | N/A |
| 47 | GPT-5.2 Pro gpt-5.2-pro-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 47.1 Agentic | 64.3 | 0.0 | 47.1 | 0.0 | 0.0 | |
| 48 | DeepSeek-V4-Pro-Max deepseek-v4-pro-max codeprogrammingtool use | DeepSeek | 46.9 Agentic | 64.3 | 85.2 | 46.9 | 52.2 | 35.4 | |
| 49 | Gemini 3.1 Pro gemini-3.1-pro-preview multimodalvisionmulti-input reasoning | Google | 46.7 Agentic | 70.6 | 85.2 | 46.7 | 61.7 | 14.0 | |
| 50 | Inkling inkling multimodalvisionmulti-input reasoning | Thinking Machines Lab | 45.7 Agentic | 34.1 | 58.2 | 45.7 | 58.9 | 30.5 | $0.95 in / $4.05 out |
| 51 | Kimi K2.7 Code kimi-k2.7-code multimodalvisionmulti-input reasoning | Moonshot AI | 45.7 Agentic | 0.0 | 41.8 | 45.7 | 0.0 | 34.6 | |
| 52 | Qwen3.7-Plus qwen3.7-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 45.1 Agentic | 61.4 | 0.0 | 45.1 | 62.1 | 0.0 | N/A |
| 53 | GPT-5.4 gpt-5.4 texttext-to-textlanguage | OpenAI | 45.0 Agentic | 69.5 | 37.6 | 45.0 | 49.1 | 13.0 | |
| 54 | Seed 2.0 Pro seed-2.0-pro multimodalvisionmulti-input reasoning | ByteDance | 45.0 Agentic | 65.6 | 30.9 | 45.0 | 56.0 | 38.2 | $0.5 in / $3 out |
| 55 | o1 o1-2024-12-17 multimodalvisionmulti-input reasoning | OpenAI | 44.7 Agentic | 41.0 | 0.0 | 44.7 | 4.9 | 0.0 | N/A |
| 56 | MiniMax M2.5 minimax-m2.5 codeprogrammingtool use | MiniMax | 43.9 Agentic | 0.0 | 65.8 | 43.9 | 50.6 | 56.8 | $0.3 in / $1.2 out |
| 57 | MiniMax M2.1 minimax-m2.1 codeprogrammingtool use | MiniMax | 43.7 Agentic | 36.9 | 65.8 | 43.7 | 48.1 | 56.8 | $0.3 in / $1.2 out |
| 58 | Seed 1.8 seed-1.8 multimodalvisionmulti-input reasoning | ByteDance | 43.1 Agentic | 50.0 | 30.9 | 43.1 | 41.2 | 47.0 | $0.25 in / $2 out |
| 59 | Kimi K2.5 kimi-k2.5 multimodalvisionmulti-input reasoning | Moonshot AI | 41.8 Agentic | 62.5 | 0.0 | 41.8 | 44.4 | 0.0 | N/A |
| 60 | Qwen3-Next-80B-A3B-Thinking qwen3-next-80b-a3b-thinking textinference | Alibaba Cloud / Qwen Team | 41.7 Agentic | 41.2 | 0.0 | 41.7 | 0.0 | 0.0 | N/A |
41
Claude Sonnet 4
Anthropic
49.4
N/A
42
Qwen3 VL 235B A22B Instruct
Alibaba Cloud / Qwen Team
49.3
$0.2 in / $0.88 out
43
Claude 3.7 Sonnet
Anthropic
49.1
N/A
44