| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 201 | Llama 3.1 8B Instruct llama-3.1-8b-instruct textinference | Meta | 25.1 overall | 3.2 | 26.7 | 0.0 | 0.0 | 83.9 | $0.03 in / $0.03 out |
| 202 | Nemotron Nano 9B v2 nvidia-nemotron-nano-9b-v2 textinference | NVIDIA | 24.9 overall | 24.9 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 203 | Llama 3.1 405B Instruct llama-3.1-405b-instruct textinference | Meta | 24.9 overall | 20.0 | 21.4 | 0.0 | 0.0 | 44.5 | $0.89 in / $0.89 out |
| 204 | DeepSeek R1 Distill Qwen 14B deepseek-r1-distill-qwen-14b textinference | DeepSeek | 24.7 overall | 24.7 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 205 | ERNIE 4.5 ernie-4.5 textinference | Baidu | 24.7 overall | 24.5 | 18.8 | 0.0 | 0.0 | 34.6 | $0.4 in / $4 out |
| 206 | GLM-4.5-Air glm-4.5-air codeprogrammingtool use | Zhipu AI | 24.5 overall | 27.7 | 0.0 | 24.9 | 20.0 | 0.0 | N/A |
| 207 | Magistral Small 2506 magistral-small-2506 textinference | Mistral AI | 24.5 overall | 24.5 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 208 | Gemini 2.5 Flash-Lite gemini-2.5-flash-lite multimodalvisionmulti-input reasoning | Google | 24.2 overall | 21.4 | 32.8 | 0.0 | 3.5 | 64.1 | |
| 209 | Qwen3-Next-80B-A3B-Instruct qwen3-next-80b-a3b-instruct textinference | Alibaba Cloud / Qwen Team | 24.0 overall | 29.5 | 6.1 | 17.9 | 0.0 | 51.9 | $0.15 in / $1.5 out |
| 210 | Grok-2 mini grok-2-mini multimodalvisionmulti-input reasoning | xAI | 24.0 overall | 24.0 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 211 | Qwen2.5 72B Instruct qwen-2.5-72b-instruct textinference | Alibaba Cloud / Qwen Team | 23.8 overall | 17.8 | 15.0 | 0.0 | 0.0 | 54.5 | $0.35 in / $0.4 out |
| 212 | GPT-4o mini gpt-4o-mini-2024-07-18 multimodalvisionmulti-input reasoning | OpenAI | 23.6 overall | 14.8 | 45.4 | 0.0 | 0.0 | 65.1 | |
| 213 | Gemma 3 4B gemma-3-4b-it multimodalvisionmulti-input reasoning | Google | 23.6 overall | 4.5 | 20.3 | 0.0 | 0.0 | 82.0 | $0.02 in / $0.04 out |
| 214 | GPT-4o gpt-4o-2024-08-06 multimodalvisionmulti-input reasoning | OpenAI | 23.5 overall | 31.5 | 46.7 | 14.9 | 4.3 | 26.8 | |
| 215 | Mistral Large 2 mistral-large-2-2407 textinference | Mistral AI | 23.5 overall | 0.0 | 21.4 | 0.0 | 0.0 | 26.7 | $2 in / $6 out |
| 216 | GPT-4 gpt-4-0613 multimodalvisionmulti-input reasoning | OpenAI | 23.2 overall | 6.8 | 54.9 | 0.0 | 0.0 | 18.7 | $30 in / $60 out |
| 217 | Phi 4 Reasoning phi-4-reasoning textinference | Microsoft | 23.1 overall | 23.1 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 218 | Llama-3.3 Nemotron Super 49B v1 llama-3.3-nemotron-super-49b-v1 textinference | NVIDIA | 23.0 overall | 23.0 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 219 | Phi-4-multimodal-instruct phi-4-multimodal-instruct multimodalvisionmulti-input reasoning | Microsoft | 23.0 overall | 8.8 | 12.3 | 0.0 | 0.0 | 79.8 | $0.05 in / $0.1 out |
| 220 | MiniMax M1 40K minimax-m1-40k codeprogrammingtool use | MiniMax | 22.6 overall | 22.6 | 0.0 | 26.8 | 18.1 | 0.0 | N/A |
201
Llama 3.1 8B Instruct
Meta
25.1
$0.03 in / $0.03 out
202
Nemotron Nano 9B v2
NVIDIA
24.9
N/A
203
Llama 3.1 405B Instruct
Meta
24.9
$0.89 in / $0.89 out
204