| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 301 | Llama-3.3 Nemotron Super 49B v1 llama-3.3-nemotron-super-49b-v1 textinference | NVIDIA | 0.0 Agentic | 20.1 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 302 | Llama 4 Maverick llama-4-maverick multimodalvisionmulti-input reasoning | Meta | 0.0 Agentic | 30.7 | 85.1 | 0.0 | 0.0 | 66.6 | $0.2 in / $0.8 out |
| 303 | Llama 4 Scout llama-4-scout multimodalvisionmulti-input reasoning | Meta | 0.0 Agentic | 25.9 | 48.6 | 0.0 | 0.0 | 85.1 | $0.1 in / $0.3 out |
| 304 | Llama Guard 4 12B llama-guard-4-12b multimodalvisionmulti-input reasoning | Meta | 0.0 Agentic | 0.0 | 21.9 | 0.0 | 0.0 | 86.7 | $0.18 in / $0.18 out |
| 305 | LongCat-Flash-Thinking longcat-flash-thinking codeprogrammingtool use | Meituan | 0.0 Agentic | 47.0 | 0.0 | 0.0 | 17.9 | 0.0 | |
| 306 | Magistral Medium magistral-medium multimodalvisionmulti-input reasoning | Mistral AI | 0.0 Agentic | 19.1 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 307 | Magistral Small 2506 magistral-small-2506 textinference | Mistral AI | 0.0 Agentic | 21.5 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 308 | MAI-Code-1.1-Flash mai-code-1.1-flash multimodalvisionmulti-input reasoning | Microsoft | 0.0 Agentic | 0.0 | 30.5 | 0.0 | 39.6 | 58.2 | $0.2 in / $1.2 out |
| 309 | MAI-Code-1-Flash mai-code-1-flash codeprogrammingtool use | Microsoft | 0.0 Agentic | 29.9 | 0.0 | 0.0 | 22.4 | 0.0 | N/A |
| 310 | MAI-Thinking-1 mai-thinking-1 codeprogrammingtool use | Microsoft | 0.0 Agentic | 58.8 | 0.0 | 0.0 | 33.9 | 0.0 | N/A |
| 311 | MedGemma 4B IT medgemma-4b-it multimodalvisionmulti-input reasoning | Google | 0.0 Agentic | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 312 | Mercury 2 mercury-2 codeprogrammingtool use | Inception | 0.0 Agentic | 41.6 | 67.3 | 0.0 | 18.6 | 72.7 | $0.25 in / $0.75 out |
| 313 | Mercury 3 mercury-3 textinference | Inception | 0.0 Agentic | 62.2 | 88.7 | 0.0 | 0.0 | 85.7 | $0.1 in / $0.35 out |
| 314 | MiMo-V2.5 mimo-v2.5 multimodalvisionmulti-input reasoning | Xiaomi | 0.0 Agentic | 47.2 | 85.1 | 0.0 | 27.5 | 78.3 | $0.168 in / $0.336 out |
| 315 | MiMo-V2.5-Pro mimo-v2.5-pro codeprogrammingtool use | Xiaomi | 0.0 Agentic | 33.9 | 85.1 | 0.0 | 55.8 | 60.6 | $0.435 in / $0.87 out |
| 316 | MiMo-V2.6-Flash mimo-v2.6-flash multimodalvisionmulti-input reasoning | Xiaomi | 0.0 Agentic | 0.0 | 85.1 | 0.0 | 0.0 | 83.4 | |
| 317 | MiMo-V2.6-Pro mimo-v2.6-pro multimodalvisionmulti-input reasoning | Xiaomi | 0.0 Agentic | 0.0 | 85.1 | 0.0 | 0.0 | 60.6 | $0.435 in / $0.87 out |
| 318 | MiMo-V2-Omni mimo-v2-omni multimodalvisionmulti-input reasoning | Xiaomi | 0.0 Agentic | 0.0 | 0.0 | 0.0 | 49.8 | 0.0 | N/A |
| 319 | MiMo-V2-Pro mimo-v2-pro codeprogrammingtool use | Xiaomi | 0.0 Agentic | 0.0 | 0.0 | 0.0 | 61.2 | 0.0 | N/A |
| 320 | MiniCPM-SALA minicpm-sala textinference | OpenBMB | 0.0 Agentic | 25.5 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
301
Llama-3.3 Nemotron Super 49B v1
NVIDIA
0.0
N/A
302
Llama 4 Maverick
Meta
0.0
$0.2 in / $0.8 out
303
Llama 4 Scout
Meta
0.0
$0.1 in / $0.3 out
304