| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 161 | Qwen3 235B A22B qwen3-235b-a22b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 29.3 overall | 29.3 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 162 | GPT-5.2 Codex gpt-5.2-codex multimodalvisionmulti-input reasoning | OpenAI | 29.1 overall | 0.0 | 31.1 | 0.0 | 30.9 | 22.0 | $1.75 in / $14 out |
| 163 | Nemotron 3 Nano (30B A3B) nemotron-3-nano-30b-a3b codeprogrammingtool use | NVIDIA | 29.0 overall | 43.6 | 32.9 | 3.0 | 3.8 | 100.0 | $0.06 in / $0.24 out |
| 164 | GPT-4.5 gpt-4.5 multimodalvisionmulti-input reasoning | OpenAI | 28.7 overall | 41.1 | 0.0 | 35.8 | 5.2 | 0.0 | N/A |
| 165 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 28.5 overall | 19.2 | 84.6 | 8.9 | 2.2 | 69.5 | |
| 166 | Mistral Large 3 (675B Instruct 2512) mistral-large-latest multimodalvisionmulti-input reasoning | Mistral AI | 28.1 overall | 21.9 | 22.0 | 0.0 | 0.0 | 55.6 | |
| 167 | Claude 3.5 Sonnet claude-3-5-sonnet-20241022 multimodalvisionmulti-input reasoning | Anthropic | 28.0 overall | 32.0 | 0.0 | 38.7 | 11.1 | 0.0 | |
| 168 | Hermes 3 70B hermes-3-70b textinference | Nous Research | 27.6 overall | 27.6 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 169 | Llama 4 Scout llama-4-scout multimodalvisionmulti-input reasoning | Meta | 27.6 overall | 27.6 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 170 | GPT-4o gpt-4o-2024-05-13 multimodalvisionmulti-input reasoning | OpenAI | 27.6 overall | 20.5 | 38.0 | 0.0 | 0.0 | 30.7 | $2.5 in / $10 out |
| 171 | Qwen3 VL 8B Thinking qwen3-vl-8b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 27.4 overall | 32.8 | 0.0 | 21.1 | 0.0 | 0.0 | N/A |
| 172 | MAI-Code-1-Flash mai-code-1-flash codeprogrammingtool use | Microsoft | 27.4 overall | 32.2 | 0.0 | 0.0 | 21.4 | 0.0 | N/A |
| 173 | Pixtral Large pixtral-large multimodalvisionmulti-input reasoning | Mistral AI | 27.3 overall | 27.3 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 174 | Command A+ command-a-plus-05-2026 multimodalvisionmulti-input reasoning | Cohere | 26.4 overall | 35.2 | 0.0 | 0.0 | 15.3 | 0.0 | |
| 175 | Qwen3 VL 30B A3B Thinking qwen3-vl-30b-a3b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 26.4 overall | 32.7 | 0.0 | 19.2 | 0.0 | 0.0 | |
| 176 | DeepSeek R1 Distill Llama 70B deepseek-r1-distill-llama-70b textinference | DeepSeek | 26.4 overall | 26.4 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 177 | QwQ-32B qwq-32b textinference | Alibaba Cloud / Qwen Team | 26.4 overall | 26.4 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 178 | QwQ-32B-Preview qwq-32b-preview textinference | Alibaba Cloud / Qwen Team | 26.4 overall | 26.4 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 179 | Nemotron 3 Super (120B A12B) nemotron-3-super-120b-a12b codeprogrammingtool use | NVIDIA | 26.2 overall | 45.5 | 0.0 | 7.6 | 22.0 | 0.0 | N/A |
| 180 | Gemini 1.5 Pro gemini-1.5-pro multimodalvisionmulti-input reasoning | Google | 26.2 overall | 26.2 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
161
Qwen3 235B A22B
Alibaba Cloud / Qwen Team
29.3
N/A
162
GPT-5.2 Codex
OpenAI
29.1
$1.75 in / $14 out
163
Nemotron 3 Nano (30B A3B)
NVIDIA
29.0
$0.06 in / $0.24 out
164