| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 181 | Nemotron 3 Super (120B A12B) nemotron-3-super-120b-a12b codeprogrammingtool use | NVIDIA | 29.1 overall | 48.3 | 0.0 | 8.7 | 26.8 | 0.0 | N/A |
| 182 | QwQ-32B qwq-32b textinference | Alibaba Cloud / Qwen Team | 28.8 overall | 28.8 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 183 | Gemini 1.0 Pro gemini-1.0-pro multimodalvisionmulti-input reasoning | Google | 28.8 overall | 3.2 | 57.2 | 0.0 | 0.0 | 55.4 | |
| 184 | Qwen3 VL 32B Instruct qwen3-vl-32b-instruct multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 28.7 overall | 29.4 | 0.0 | 27.9 | 0.0 | 0.0 | |
| 185 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 28.7 overall | 20.7 | 90.6 | 8.9 | 2.6 | 56.8 | |
| 186 | Mistral Small 3 24B Instruct mistral-small-24b-instruct-2501 textinference | Mistral AI | 28.6 overall | 14.2 | 21.4 | 0.0 | 0.0 | 80.7 | $0.07 in / $0.14 out |
| 187 | o3-mini o3-mini codeprogrammingtool use | OpenAI | 28.1 overall | 25.6 | 70.4 | 11.9 | 12.2 | 41.6 | $1.1 in / $4.4 out |
| 188 | Qwen3 32B qwen3-32b textinference | Alibaba Cloud / Qwen Team | 28.0 overall | 21.4 | 13.3 | 0.0 | 0.0 | 69.8 | $0.1 in / $0.3 out |
| 189 | GPT-4 Turbo gpt-4-turbo-2024-04-09 textinference | OpenAI | 27.9 overall | 16.9 | 52.7 | 0.0 | 0.0 | 18.8 | $10 in / $30 out |
| 190 | o1 o1-2024-12-17 multimodalvisionmulti-input reasoning | OpenAI | 27.8 overall | 42.9 | 19.4 | 44.7 | 6.5 | 4.9 | $15 in / $60 out |
| 191 | MiniCPM-SALA minicpm-sala textinference | OpenBMB | 27.5 overall | 27.5 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 192 | Kimi K2 Instruct kimi-k2-instruct codeprogrammingtool use | Moonshot AI | 27.3 overall | 24.4 | 46.1 | 14.8 | 15.3 | 62.1 | $0.5 in / $0.5 out |
| 193 | GPT-4.5 gpt-4.5 multimodalvisionmulti-input reasoning | OpenAI | 27.1 overall | 41.9 | 29.7 | 35.8 | 6.0 | 7.0 | $75 in / $150 out |
| 194 | Kimi K2 Base kimi-k2-base textinference | Moonshot AI | 26.9 overall | 26.9 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 195 | o1-preview o1-preview codeprogrammingtool use | OpenAI | 26.6 overall | 41.8 | 33.0 | 0.0 | 9.5 | 11.8 | $15 in / $60 out |
| 196 | Sarvam-105B sarvam-105b codeprogrammingtool use | Sarvam AI | 25.7 overall | 42.9 | 0.0 | 17.9 | 12.1 | 0.0 | N/A |
| 197 | Gemma 3 12B gemma-3-12b-it multimodalvisionmulti-input reasoning | Google | 25.7 overall | 9.1 | 20.3 | 0.0 | 0.0 | 80.7 | $0.05 in / $0.1 out |
| 198 | Llama 3.1 70B Instruct llama-3.1-70b-instruct textinference | Meta | 25.5 overall | 11.2 | 21.4 | 0.0 | 0.0 | 72.2 | $0.2 in / $0.2 out |
| 199 | Gemma 3 27B gemma-3-27b-it multimodalvisionmulti-input reasoning | Google | 25.3 overall | 10.7 | 20.3 | 0.0 | 0.0 | 73.9 | $0.1 in / $0.2 out |
| 200 | Phi 4 phi-4 textinference | Microsoft | 25.1 overall | 15.6 | 9.0 | 0.0 | 0.0 | 77.2 | $0.07 in / $0.14 out |
181
Nemotron 3 Super (120B A12B)
NVIDIA
29.1
N/A
182
QwQ-32B
Alibaba Cloud / Qwen Team
28.8
N/A
183Google
Gemini 1.0 Pro
28.8
$0.5 in / $1.5 out
184