| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 221 | DeepSeek-R1 deepseek-r1 textinference | DeepSeek | 22.3 overall | 0.0 | 14.3 | 0.0 | 0.0 | 35.1 | $0.55 in / $2.19 out |
| 222 | Magistral Medium magistral-medium multimodalvisionmulti-input reasoning | Mistral AI | 22.2 overall | 22.2 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 223 | Mistral Large 3 (675B Base) mistral-large-3-675b-base-2512 multimodalvisionmulti-input reasoning | Mistral AI | 22.2 overall | 22.2 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 224 | Mistral Large 3 (675B Instruct 2512 Eagle) mistral-large-3-675B-instruct-2512-eagle multimodalvisionmulti-input reasoning | Mistral AI | 22.2 overall | 22.2 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 225 | Mistral Large 3 (675B Instruct 2512 NVFP4) mistral-large-3-675b-instruct-2512-nvfp4 multimodalvisionmulti-input reasoning | Mistral AI | 22.2 overall | 22.2 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 226 | Llama 3.2 90B Instruct llama-3.2-90b-instruct multimodalvisionmulti-input reasoning | Meta | 22.0 overall | 16.3 | 11.3 | 0.0 | 0.0 | 54.9 | $0.35 in / $0.4 out |
| 227 | Sarvam-30B sarvam-30b codeprogrammingtool use | Sarvam AI | 21.7 overall | 46.4 | 0.0 | 8.2 | 5.2 | 0.0 | N/A |
| 228 | Phi 4 Mini Reasoning phi-4-mini-reasoning textinference | Microsoft | 21.7 overall | 21.7 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 229 | DeepSeek-R1-0528 deepseek-r1-0528 codeprogrammingtool use | DeepSeek | 21.3 overall | 50.1 | 14.3 | 0.0 | 6.6 | 35.1 | $0.55 in / $2.19 out |
| 230 | GPT-3.5 Turbo gpt-3.5-turbo-0125 multimodalvisionmulti-input reasoning | OpenAI | 21.3 overall | 2.5 | 36.7 | 0.0 | 0.0 | 49.4 | |
| 231 | Mistral Small mistral-small-2409 textinference | Mistral AI | 21.3 overall | 0.0 | 2.1 | 0.0 | 0.0 | 51.9 | $0.2 in / $0.6 out |
| 232 | Pixtral Large pixtral-large multimodalvisionmulti-input reasoning | Mistral AI | 20.6 overall | 27.8 | 7.0 | 0.0 | 0.0 | 22.4 | |
| 233 | GPT-5 nano gpt-5-nano-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 19.9 overall | 26.3 | 0.0 | 0.0 | 11.8 | 0.0 | |
| 234 | Pixtral-12B pixtral-12b-2409 multimodalvisionmulti-input reasoning | Mistral AI | 19.8 overall | 8.1 | 7.0 | 0.0 | 0.0 | 73.0 | |
| 235 | Gemma 4 E4B gemma-4-e4b-it multimodalvisionmulti-input reasoning | Google | 19.2 overall | 19.2 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 236 | Mistral Small 3.2 24B Instruct mistral-small-3.2-24b-instruct-2506 multimodalvisionmulti-input reasoning | Mistral AI | 19.1 overall | 19.1 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 237 | Phi-3.5-mini-instruct phi-3.5-mini-instruct multimodalvisionmulti-input reasoning | Microsoft | 18.9 overall | 2.7 | 10.8 | 0.0 | 0.0 | 77.2 | $0.1 in / $0.1 out |
| 238 | Jamba 1.5 Large jamba-1.5-large textinference | AI21 Labs | 18.8 overall | 8.1 | 33.6 | 0.0 | 0.0 | 25.2 | $2 in / $8 out |
| 239 | Qwen2.5 32B Instruct qwen-2.5-32b-instruct textinference | Alibaba Cloud / Qwen Team | 18.6 overall | 18.6 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 240 | DeepSeek R1 Distill Qwen 7B deepseek-r1-distill-qwen-7b textinference | DeepSeek | 18.3 overall | 18.3 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
221
DeepSeek-R1
DeepSeek
22.3
$0.55 in / $2.19 out
222
Magistral Medium
Mistral AI
22.2
N/A
223
Mistral Large 3 (675B Base)
Mistral AI
22.2
N/A
224