| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 41 | MiniMax M2 minimax-m2 codeprogrammingtool use | MiniMax | 41.4 Agentic | 32.2 | 55.9 | 41.4 | 42.8 | 52.3 | $0.3 in / $1.2 out |
| 42 | Qwen3 VL 235B A22B Thinking qwen3-vl-235b-a22b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 40.2 Agentic | 37.9 | 66.8 | 40.2 | 0.0 | 37.2 | |
| 43 | Claude 3.5 Sonnet claude-3-5-sonnet-20241022 multimodalvisionmulti-input reasoning | Anthropic | 38.7 Agentic | 33.9 | 67.4 | 38.7 | 13.2 | 24.5 | |
| 44 | o4-mini o4-mini multimodalvisionmulti-input reasoning | OpenAI | 38.2 Agentic | 48.8 | 70.7 | 38.2 | 32.7 | 41.9 | $1.1 in / $4.4 out |
| 45 | GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning | Zhipu AI | 37.7 Agentic | 47.0 | 34.9 | 37.7 | 46.1 | 42.8 | $0.55 in / $2.19 out |
| 46 | GLM-4.5 glm-4.5 codeprogrammingtool use | Zhipu AI | 36.4 Agentic | 34.3 | 0.0 | 36.4 | 40.6 | 0.0 | N/A |
| 47 | GPT-4.5 gpt-4.5 multimodalvisionmulti-input reasoning | OpenAI | 35.8 Agentic | 41.9 | 29.1 | 35.8 | 6.2 | 6.8 | $75 in / $150 out |
| 48 | Qwen3.5-397B-A17B qwen3.5-397b-a17b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 35.6 Agentic | 58.6 | 66.8 | 35.6 | 60.9 | 35.3 | $0.6 in / $3.6 out |
| 49 | Qwen3 VL 32B Thinking qwen3-vl-32b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 34.6 Agentic | 44.6 | 0.0 | 34.6 | 0.0 | 0.0 | |
| 50 | GPT-4.1 gpt-4.1-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 32.8 Agentic | 28.8 | 75.4 | 32.8 | 17.7 | 34.6 | |
| 51 | LongCat-Flash-Thinking-2601 longcat-flash-thinking-2601 codeprogrammingtool use | Meituan | 30.8 Agentic | 56.3 | 51.9 | 30.8 | 38.0 | 57.7 | |
| 52 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 29.5 Agentic | 24.7 | 83.8 | 29.5 | 25.3 | 83.3 | $0.1 in / $0.4 out |
| 53 | GPT-5 gpt-5-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 29.0 Agentic | 64.4 | 0.0 | 29.0 | 51.7 | 0.0 | N/A |
| 54 | DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use | DeepSeek | 28.8 Agentic | 52.7 | 0.0 | 28.8 | 40.5 | 0.0 | N/A |
| 55 | GLM-4.7 glm-4.7 multimodalvisionmulti-input reasoning | Zhipu AI | 28.2 Agentic | 63.2 | 52.8 | 28.2 | 44.5 | 40.6 | $0.6 in / $2.2 out |
| 56 | Qwen3 VL 32B Instruct qwen3-vl-32b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 27.9 Agentic | 29.5 | 0.0 | 27.9 | 0.0 | 0.0 | |
| 57 | MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use | Xiaomi | 27.2 Agentic | 53.7 | 79.8 | 27.2 | 39.3 | 85.9 | $0.1 in / $0.3 out |
| 58 | GPT-5.4 Mini gpt-5.4-mini texttext-to-textlanguage | OpenAI | 27.1 Agentic | 57.4 | 77.4 | 27.1 | 26.9 | 32.8 | |
| 59 | GPT OSS 120B gpt-oss-120b textinference | OpenAI | 26.8 Agentic | 36.6 | 34.9 | 26.8 | 0.0 | 76.7 | $0.09 in / $0.45 out |
| 60 | MiniMax M1 40K minimax-m1-40k codeprogrammingtool use | MiniMax | 26.8 Agentic | 22.9 | 0.0 | 26.8 | 18.5 | 0.0 | N/A |
41
MiniMax M2
MiniMax
41.4
$0.3 in / $1.2 out
42
Qwen3 VL 235B A22B Thinking
Alibaba Cloud / Qwen Team
40.2
$0.45 in / $3.49 out
43
Claude 3.5 Sonnet
Anthropic
38.7
$3 in / $15 out
44