| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 81 | DeepSeek-V4-Flash-Max deepseek-v4-flash-max codeprogrammingtool use | DeepSeek | 33.5 Agentic | 55.5 | 85.2 | 33.5 | 43.9 | 90.4 | $0.09 in / $0.18 out |
| 82 | Qwen3 VL 235B A22B Thinking qwen3-vl-235b-a22b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 33.3 Agentic | 33.9 | 0.0 | 33.3 | 0.0 | 0.0 | |
| 83 | GPT-4.1 gpt-4.1-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 32.8 Agentic | 25.9 | 68.7 | 32.8 | 14.2 | 30.2 | |
| 84 | Ling 3.0 Flash ling-3.0-flash codeprogrammingtool use | InclusionAI | 30.3 Agentic | 0.0 | 15.0 | 30.3 | 33.7 | 93.1 | $0.06 in / $0.18 out |
| 85 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 30.1 Agentic | 21.7 | 75.2 | 30.1 | 23.6 | 83.7 | $0.1 in / $0.4 out |
| 86 | Qwen3.6 Plus qwen3.6-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 29.9 Agentic | 65.4 | 66.7 | 29.9 | 53.6 | 38.2 | $0.5 in / $3 out |
| 87 | Qwen3 VL 32B Thinking qwen3-vl-32b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 28.9 Agentic | 39.1 | 0.0 | 28.9 | 0.0 | 0.0 | |
| 88 | Gemini 3 Flash gemini-3-flash-preview multimodalvisionmulti-input reasoning | Google | 28.2 Agentic | 67.5 | 66.7 | 28.2 | 61.8 | 38.2 | |
| 89 | DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use | DeepSeek | 27.1 Agentic | 48.7 | 0.0 | 27.1 | 37.5 | 0.0 | N/A |
| 90 | GPT OSS 120B gpt-oss-120b textinference | OpenAI | 26.8 Agentic | 31.6 | 15.0 | 26.8 | 0.0 | 95.1 | $0.037 in / $0.17 out |
| 91 | MiniMax M1 40K minimax-m1-40k codeprogrammingtool use | MiniMax | 26.8 Agentic | 20.3 | 0.0 | 26.8 | 14.8 | 0.0 | N/A |
| 92 | Qwen3-235B-A22B-Thinking-2507 qwen3-235b-a22b-thinking-2507 textinference | Alibaba Cloud / Qwen Team | 26.8 Agentic | 42.5 | 0.0 | 26.8 | 0.0 | 0.0 | N/A |
| 93 | GLM-4.7 glm-4.7 multimodalvisionmulti-input reasoning | Zhipu AI | 25.7 Agentic | 59.4 | 26.2 | 25.7 | 42.3 | 47.8 | $0.4 in / $1.75 out |
| 94 | LongCat-Flash-Thinking-2601 longcat-flash-thinking-2601 codeprogrammingtool use | Meituan | 25.7 Agentic | 50.7 | 0.0 | 25.7 | 31.8 | 0.0 | |
| 95 | GPT-5 gpt-5-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 24.6 Agentic | 58.5 | 0.0 | 24.6 | 46.5 | 0.0 | N/A |
| 96 | GLM-4.5-Air glm-4.5-air codeprogrammingtool use | Zhipu AI | 24.2 Agentic | 23.7 | 0.0 | 24.2 | 18.3 | 0.0 | N/A |
| 97 | Qwen3.5-397B-A17B qwen3.5-397b-a17b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 23.8 Agentic | 52.4 | 41.8 | 23.8 | 55.3 | 39.6 | $0.45 in / $3 out |
| 98 | DeepSeek-V4-Flash-0423 deepseek-v4-flash-0423 codeprogrammingtool use | DeepSeek | 23.7 Agentic | 51.4 | 85.2 | 23.7 | 40.7 | 90.4 | |
| 99 | MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use | Xiaomi | 23.4 Agentic | 48.6 | 0.0 | 23.4 | 35.9 | 0.0 | N/A |
| 100 | Qwen3 VL 32B Instruct qwen3-vl-32b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 23.0 Agentic | 24.2 | 0.0 | 23.0 | 0.0 | 0.0 |
81
DeepSeek-V4-Flash-Max
DeepSeek
33.5
$0.09 in / $0.18 out
82
Qwen3 VL 235B A22B Thinking
Alibaba Cloud / Qwen Team
33.3
N/A
83
GPT-4.1
OpenAI
32.8
$2 in / $8 out
84