| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 201 | Mistral Medium 3.5 mistral-medium-3-5 multimodalvisionmulti-input reasoning | Mistral AI | 33.0 overall | 34.0 | 30.9 | 13.9 | 58.9 | 22.3 | $1.5 in / $7.5 out |
| 202 | DeepSeek-V3.2-Speciale deepseek-v3.2-speciale codeprogrammingtool use | DeepSeek | 32.8 overall | 48.8 | 0.0 | 5.3 | 42.5 | 0.0 | |
| 203 | Nemotron 3.5 Bolt (74B A9B 24GB) nemotron-3.5-bolt-74b-a9b-24gb multimodalvisionmulti-input reasoning | NVIDIA | 32.8 overall | 46.6 | 0.0 | 18.6 | 30.7 | 0.0 | |
| 204 | GPT-5.4 Mini gpt-5.4-mini texttext-to-textlanguage | OpenAI | 32.7 overall | 48.4 | 52.5 | 12.9 | 21.6 | 29.1 | |
| 205 | GPT-4.1 nano gpt-4.1-nano-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 32.5 overall | 10.8 | 87.5 | 0.0 | 0.0 | 82.9 | |
| 206 | Qwen3 30B A3B qwen3-30b-a3b textinference | Alibaba Cloud / Qwen Team | 32.4 overall | 22.7 | 26.3 | 0.0 | 0.0 | 69.6 | $0.1 in / $0.44 out |
| 207 | Qwen3 VL 30B A3B Instruct qwen3-vl-30b-a3b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 32.3 overall | 24.2 | 41.8 | 19.3 | 0.0 | 70.9 | |
| 208 | GPT-5.6 Cyber gpt-5.6-cyber multimodalvisionmulti-input reasoning | OpenAI | 32.3 overall | 0.0 | 52.5 | 0.0 | 0.0 | 0.0 | $12.5 in / $75 out |
| 209 | GPT-4.1 gpt-4.1-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 32.2 overall | 25.9 | 68.7 | 32.8 | 14.2 | 30.2 | |
| 210 | Llama 3.1 Nemotron Ultra 253B v1 llama-3.1-nemotron-ultra-253b-v1 textinference | NVIDIA | 31.7 overall | 31.7 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 211 | Qwen3-Next-80B-A3B-Instruct qwen3-next-80b-a3b-instruct textinference | Alibaba Cloud / Qwen Team | 31.6 overall | 26.1 | 41.8 | 17.9 | 0.0 | 63.7 | $0.09 in / $1.1 out |
| 212 | o1 o1-2024-12-17 multimodalvisionmulti-input reasoning | OpenAI | 31.5 overall | 41.0 | 0.0 | 44.7 | 4.9 | 0.0 | N/A |
| 213 | Gemma 4 E4B gemma-4-e4b-it multimodalvisionmulti-input reasoning | Google | 31.1 overall | 16.3 | 15.0 | 0.0 | 0.0 | 98.4 | $0.02 in / $0.1 out |
| 214 | Sakana Namazu sakana-namazu multimodalvisionmulti-input reasoning | Sakana AI | 31.0 overall | 0.0 | 30.9 | 0.0 | 0.0 | 31.3 | $0.95 in / $4 out |
| 215 | GPT-5.3 Codex gpt-5.3-codex texttext-to-textcoding | OpenAI | 30.3 overall | 0.0 | 32.9 | 0.0 | 35.6 | 14.5 | |
| 216 | Gemma 4 12B gemma-4-12b-it multimodalvisionmulti-input reasoning | Google | 30.1 overall | 30.1 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 217 | MiniMax M2.7 minimax-m2.7 codeprogrammingtool use | MiniMax | 30.0 overall | 0.0 | 27.3 | 22.1 | 29.2 | 54.7 | $0.3 in / $1.2 out |
| 218 | Gemini 2.0 Flash gemini-2.0-flash multimodalvisionmulti-input reasoning | Google | 29.8 overall | 29.8 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 219 | o3 o3-2025-04-16 multimodalvisionmulti-input reasoning | OpenAI | 29.5 overall | 42.3 | 0.0 | 17.1 | 26.8 | 0.0 | N/A |
| 220 | Nemotron 3 Nano (30B A3B) nemotron-3-nano-30b-a3b codeprogrammingtool use | NVIDIA | 29.5 overall | 42.1 | 41.8 | 3.0 | 5.3 | 91.5 | $0.05 in / $0.2 out |
201
Mistral Medium 3.5
Mistral AI
33.0
$1.5 in / $7.5 out
202
DeepSeek-V3.2-Speciale
DeepSeek
32.8
N/A
203
Nemotron 3.5 Bolt (74B A9B 24GB)
NVIDIA
32.8
N/A
204