| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 61 | GLM-4.7 glm-4.7 multimodalvisionmulti-input reasoning | Zhipu AI | 28.0 Agentic | 62.3 | 0.0 | 28.0 | 43.6 | 0.0 | N/A |
| 62 | GPT-5 gpt-5-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 27.5 Agentic | 63.8 | 0.0 | 27.5 | 50.6 | 0.0 | N/A |
| 63 | Qwen3 VL 32B Instruct qwen3-vl-32b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 27.2 Agentic | 28.6 | 0.0 | 27.2 | 0.0 | 0.0 | |
| 64 | GPT OSS 120B gpt-oss-120b textinference | OpenAI | 26.8 Agentic | 34.9 | 14.6 | 26.8 | 0.0 | 90.5 | $0.09 in / $0.45 out |
| 65 | MiniMax M1 40K minimax-m1-40k codeprogrammingtool use | MiniMax | 26.8 Agentic | 21.8 | 0.0 | 26.8 | 16.6 | 0.0 | N/A |
| 66 | Qwen3-235B-A22B-Thinking-2507 qwen3-235b-a22b-thinking-2507 textinference | Alibaba Cloud / Qwen Team | 26.8 Agentic | 45.8 | 0.0 | 26.8 | 0.0 | 0.0 | N/A |
| 67 | Qwen3 VL 8B Instruct qwen3-vl-8b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 26.4 Agentic | 8.8 | 41.1 | 26.4 | 0.0 | 87.3 | $0.08 in / $0.5 out |
| 68 | MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use | Xiaomi | 25.3 Agentic | 52.4 | 0.0 | 25.3 | 36.8 | 0.0 | N/A |
| 69 | GLM-4.5-Air glm-4.5-air codeprogrammingtool use | Zhipu AI | 24.3 Agentic | 26.7 | 0.0 | 24.3 | 18.3 | 0.0 | N/A |
| 70 | Qwen3 VL 8B Thinking qwen3-vl-8b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 23.3 Agentic | 34.1 | 41.1 | 23.3 | 0.0 | 54.4 | |
| 71 | Qwen3 VL 30B A3B Instruct qwen3-vl-30b-a3b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 22.9 Agentic | 27.0 | 0.0 | 22.9 | 0.0 | 0.0 | |
| 72 | GPT-5.4 Mini gpt-5.4-mini texttext-to-textlanguage | OpenAI | 22.4 Agentic | 56.9 | 56.3 | 22.4 | 27.4 | 32.9 | |
| 73 | MiniMax M1 80K minimax-m1-80k codeprogrammingtool use | MiniMax | 20.9 Agentic | 23.4 | 0.0 | 20.9 | 17.4 | 0.0 | N/A |
| 74 | Qwen3 VL 30B A3B Thinking qwen3-vl-30b-a3b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 20.7 Agentic | 34.1 | 0.0 | 20.7 | 0.0 | 0.0 | |
| 75 | o3 o3-2025-04-16 multimodalvisionmulti-input reasoning | OpenAI | 19.8 Agentic | 45.7 | 0.0 | 19.8 | 29.9 | 0.0 | N/A |
| 76 | Qwen3 VL 4B Instruct qwen3-vl-4b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 18.8 Agentic | 18.9 | 41.1 | 18.8 | 0.0 | 81.0 | |
| 77 | Qwen3 VL 4B Thinking qwen3-vl-4b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 18.6 Agentic | 21.6 | 41.1 | 18.6 | 0.0 | 73.4 | |
| 78 | Sarvam-105B sarvam-105b codeprogrammingtool use | Sarvam AI | 18.3 Agentic | 42.1 | 0.0 | 18.3 | 11.1 | 0.0 | N/A |
| 79 | Qwen3-Next-80B-A3B-Instruct qwen3-next-80b-a3b-instruct textinference | Alibaba Cloud / Qwen Team | 17.9 Agentic | 28.4 | 0.0 | 17.9 | 0.0 | 0.0 | N/A |
| 80 | Mistral Medium 3.5 mistral-medium-3-5 multimodalvisionmulti-input reasoning | Mistral AI | 16.8 Agentic | 34.9 | 28.5 | 16.8 | 61.7 | 29.1 |
61
GLM-4.7
Zhipu AI
28.0
N/A
62
GPT-5
OpenAI
27.5
N/A
63
Qwen3 VL 32B Instruct
Alibaba Cloud / Qwen Team
27.2
N/A
64