| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 101 | Gemini 2.5 Pro Preview 06-05 gemini-2.5-pro-preview-06-05 multimodalvisionmulti-input reasoning | Google | 44.2 overall | 51.2 | 62.8 | 0.0 | 29.3 | 27.6 | $1.25 in / $10 out |
| 102 | Qwen3 VL 235B A22B Thinking qwen3-vl-235b-a22b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 44.2 overall | 37.7 | 66.0 | 40.2 | 0.0 | 37.4 | |
| 103 | Nova Lite nova-lite multimodalvisionmulti-input reasoning | Amazon | 44.0 overall | 13.5 | 70.5 | 0.0 | 0.0 | 86.7 | $0.06 in / $0.24 out |
| 104 | Grok Code Fast 1 grok-code-fast-1 codeprogrammingtool use | xAI | 44.0 overall | 0.0 | 47.7 | 0.0 | 38.8 | 49.7 | $0.2 in / $1.5 out |
| 105 | Devstral Medium devstral-medium-2507 codeprogrammingtool use | Mistral AI | 43.8 overall | 0.0 | 64.8 | 0.0 | 24.2 | 53.4 | $0.4 in / $2 out |
| 106 | Qwen3-Coder 480B A35B Instruct qwen3-coder-480b-a35b-instruct codeprogrammingtool use | Alibaba Cloud / Qwen Team | 43.6 overall | 0.0 | 0.0 | 50.7 | 35.8 | 0.0 | |
| 107 | Qwen3-235B-A22B-Thinking-2507 qwen3-235b-a22b-thinking-2507 textinference | Alibaba Cloud / Qwen Team | 43.5 overall | 46.4 | 66.0 | 26.8 | 0.0 | 39.6 | $0.3 in / $3 out |
| 108 | GPT-5.4 Mini gpt-5.4-mini texttext-to-textlanguage | OpenAI | 43.3 overall | 56.8 | 76.5 | 23.8 | 28.1 | 32.4 | |
| 109 | Mistral NeMo Instruct mistral-nemo-instruct-2407 textinference | Mistral AI | 42.9 overall | 0.0 | 21.4 | 0.0 | 0.0 | 77.3 | $0.15 in / $0.15 out |
| 110 | GPT-5.3 Chat gpt-5.3-chat-latest multimodalvisionmulti-input reasoning | OpenAI | 42.6 overall | 0.0 | 52.7 | 0.0 | 0.0 | 26.5 | |
| 111 | LongCat-Flash-Chat longcat-flash-chat codeprogrammingtool use | Meituan | 42.4 overall | 27.9 | 52.7 | 49.2 | 39.1 | 57.9 | $0.3 in / $1.2 out |
| 112 | Mistral Small 3.1 24B Base mistral-small-3.1-24b-base-2503 multimodalvisionmulti-input reasoning | Mistral AI | 42.0 overall | 13.4 | 64.8 | 0.0 | 0.0 | 85.3 | |
| 113 | GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning | Zhipu AI | 41.8 overall | 46.5 | 34.5 | 37.3 | 45.7 | 42.9 | $0.55 in / $2.19 out |
| 114 | Llama 3.2 3B Instruct llama-3.2-3b-instruct textinference | Meta | 41.4 overall | 5.2 | 68.9 | 0.0 | 0.0 | 98.8 | $0.01 in / $0.02 out |
| 115 | Qwen3 235B A22B qwen3-235b-a22b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 41.3 overall | 30.5 | 33.5 | 0.0 | 0.0 | 84.0 | $0.1 in / $0.1 out |
| 116 | Command R+ command-r-plus-04-2024 textinference | Cohere | 41.3 overall | 0.0 | 32.5 | 0.0 | 0.0 | 55.4 | $0.25 in / $1 out |
| 117 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 41.1 overall | 24.5 | 83.6 | 29.5 | 25.1 | 83.1 | $0.1 in / $0.4 out |
| 118 | DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use | DeepSeek | 41.0 overall | 52.3 | 0.0 | 28.6 | 40.1 | 0.0 | N/A |
| 119 | GPT-5.2 Codex gpt-5.2-codex multimodalvisionmulti-input reasoning | OpenAI | 40.6 overall | 0.0 | 49.0 | 0.0 | 44.1 | 19.6 | $1.75 in / $14 out |
| 120 | Gemini 2.5 Pro gemini-2.5-pro multimodalvisionmulti-input reasoning | Google | 40.4 overall | 44.2 | 62.8 | 0.0 | 25.0 | 27.6 |
101Google
Gemini 2.5 Pro Preview 06-05
44.2
$1.25 in / $10 out
102
Qwen3 VL 235B A22B Thinking
Alibaba Cloud / Qwen Team
44.2
$0.45 in / $3.49 out
103
Nova Lite
Amazon
44.0
$0.06 in / $0.24 out
104