| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 61 | Qwen3-235B-A22B-Thinking-2507 qwen3-235b-a22b-thinking-2507 textinference | Alibaba Cloud / Qwen Team | 26.8 Agentic | 46.9 | 66.8 | 26.8 | 0.0 | 39.4 | $0.3 in / $3 out |
| 62 | Qwen3 VL 8B Instruct qwen3-vl-8b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 26.7 Agentic | 9.8 | 66.8 | 26.7 | 0.0 | 75.6 | $0.08 in / $0.5 out |
| 63 | GLM-4.5-Air glm-4.5-air codeprogrammingtool use | Zhipu AI | 24.9 Agentic | 28.1 | 0.0 | 24.9 | 20.2 | 0.0 | N/A |
| 64 | Qwen3 VL 30B A3B Instruct qwen3-vl-30b-a3b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 23.6 Agentic | 28.7 | 66.8 | 23.6 | 0.0 | 63.3 | |
| 65 | Qwen3 VL 8B Thinking qwen3-vl-8b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 23.5 Agentic | 35.9 | 66.8 | 23.5 | 0.0 | 45.6 | |
| 66 | Qwen3 VL 30B A3B Thinking qwen3-vl-30b-a3b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 21.3 Agentic | 35.5 | 66.8 | 21.3 | 0.0 | 60.0 | |
| 67 | MiniMax M1 80K minimax-m1-80k codeprogrammingtool use | MiniMax | 20.9 Agentic | 24.6 | 84.9 | 20.9 | 19.4 | 41.7 | $0.55 in / $2.2 out |
| 68 | o3 o3-2025-04-16 multimodalvisionmulti-input reasoning | OpenAI | 20.5 Agentic | 46.2 | 38.4 | 20.5 | 30.7 | 27.7 | $2 in / $8 out |
| 69 | Qwen3 VL 4B Instruct qwen3-vl-4b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 19.5 Agentic | 19.7 | 66.8 | 19.5 | 0.0 | 70.6 | |
| 70 | Qwen3 VL 4B Thinking qwen3-vl-4b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 18.9 Agentic | 23.1 | 66.8 | 18.9 | 0.0 | 60.6 | |
| 71 | Sarvam-105B sarvam-105b codeprogrammingtool use | Sarvam AI | 18.8 Agentic | 43.2 | 0.0 | 18.8 | 12.4 | 0.0 | N/A |
| 72 | Qwen3-Next-80B-A3B-Instruct qwen3-next-80b-a3b-instruct textinference | Alibaba Cloud / Qwen Team | 17.9 Agentic | 29.7 | 6.1 | 17.9 | 0.0 | 51.9 | $0.15 in / $1.5 out |
| 73 | Qwen3.6-35B-A3B qwen3.6-35b-a3b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 17.7 Agentic | 55.7 | 0.0 | 17.7 | 26.6 | 0.0 | N/A |
| 74 | DeepSeek-V3.2 (Thinking) deepseek-reasoner codeprogrammingtool use | DeepSeek | 16.6 Agentic | 53.1 | 0.0 | 16.6 | 45.9 | 0.0 | N/A |
| 75 | DeepSeek-V3.2 deepseek-v3.2 codeprogrammingtool use | DeepSeek | 16.6 Agentic | 58.1 | 52.5 | 16.6 | 45.9 | 70.0 | $0.26 in / $0.38 out |
| 76 | Grok 4 Fast grok-4-fast multimodalvisionmulti-input reasoning | xAI | 15.4 Agentic | 58.0 | 68.2 | 15.4 | 0.0 | 67.2 | $0.2 in / $0.5 out |
| 77 | DeepSeek-V3.1 deepseek-v3.1 codeprogrammingtool use | DeepSeek | 15.3 Agentic | 38.7 | 40.2 | 15.3 | 28.7 | 58.9 | $0.27 in / $1 out |
| 78 | GPT-4o gpt-4o-2024-08-06 multimodalvisionmulti-input reasoning | OpenAI | 14.9 Agentic | 31.6 | 45.9 | 14.9 | 4.4 | 26.8 | |
| 79 | Kimi K2 Instruct kimi-k2-instruct codeprogrammingtool use | Moonshot AI | 14.8 Agentic | 24.9 | 46.6 | 14.8 | 15.3 | 61.7 | $0.5 in / $0.5 out |
| 80 | GLM-4.7-Flash glm-4.7-flash codeprogrammingtool use | Zhipu AI | 12.0 Agentic | 38.5 | 29.1 | 12.0 | 21.2 | 72.2 | $0.07 in / $0.4 out |
61
Qwen3-235B-A22B-Thinking-2507
Alibaba Cloud / Qwen Team
26.8
$0.3 in / $3 out
62
Qwen3 VL 8B Instruct
Alibaba Cloud / Qwen Team
26.7
$0.08 in / $0.5 out
63
GLM-4.5-Air
Zhipu AI
24.9
N/A
64