| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | Nemotron 3.5 Lightning (30B A3B) nemotron-3.5-lightning-30b-a3b codeprogrammingtool use | NVIDIA | 89.0 Value / Price | 26.3 | 41.8 | 6.4 | 8.2 | 89.0 | $0.08 in / $0.2 out |
| 22 | Laguna S 2.1 laguna-s-2.1 codeprogrammingtool use | Poolside | 88.2 Value / Price | 0.0 | 85.2 | 33.7 | 50.8 | 88.2 | $0.1 in / $0.2 out |
| 23 | Laguna XS 2.1 laguna-xs-2.1 codeprogrammingtool use | Poolside | 88.2 Value / Price | 0.0 | 41.8 | 0.0 | 21.4 | 88.2 | $0.1 in / $0.2 out |
| 24 | IBM Granite 4.2 8B granite-4.2-8b codeprogrammingtool use | IBM | 87.4 Value / Price | 30.1 | 15.0 | 0.0 | 8.4 | 87.4 | $0.06 in / $0.25 out |
| 25 | Llama Guard 4 12B llama-guard-4-12b multimodalvisionmulti-input reasoning | Meta | 86.5 Value / Price | 0.0 | 22.1 | 0.0 | 0.0 | 86.5 | $0.18 in / $0.18 out |
| 26 | Qwen3 14B qwen3-14b textinference | Alibaba Cloud / Qwen Team | 86.5 Value / Price | 15.8 | 3.8 | 0.0 | 0.0 | 86.5 | $0.12 in / $0.24 out |
| 27 | Qwen3 32B qwen3-32b textinference | Alibaba Cloud / Qwen Team | 85.7 Value / Price | 20.0 | 7.1 | 0.0 | 0.0 | 85.7 | $0.08 in / $0.28 out |
| 28 | Llama 4 Scout llama-4-scout multimodalvisionmulti-input reasoning | Meta | 84.9 Value / Price | 25.9 | 49.2 | 0.0 | 0.0 | 84.9 | $0.1 in / $0.3 out |
| 29 | Nemotron Content Safety 3.5 nemotron-content-safety-3.5 multimodalvisionmulti-input reasoning | NVIDIA | 84.9 Value / Price | 0.0 | 15.0 | 0.0 | 0.0 | 84.9 | |
| 30 | Gemma 4 26B-A4B gemma-4-26b-a4b-it multimodalvisionmulti-input reasoning | Google | 84.1 Value / Price | 41.5 | 41.8 | 0.0 | 0.0 | 84.1 | |
| 31 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 83.7 Value / Price | 21.7 | 75.2 | 30.1 | 23.6 | 83.7 | |
| 32 | Llama 3.3 70B Instruct llama-3.3-70b-instruct textinference | Meta | 83.2 Value / Price | 16.5 | 15.0 | 0.0 | 0.0 | 83.2 | $0.1 in / $0.32 out |
| 33 | MiMo-V2.6-Flash mimo-v2.6-flash multimodalvisionmulti-input reasoning | Xiaomi | 83.2 Value / Price | 0.0 | 85.2 | 0.0 | 0.0 | 83.2 | |
| 34 | GPT-4.1 nano gpt-4.1-nano-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 82.9 Value / Price | 10.8 | 87.5 | 0.0 | 0.0 | 82.9 | |
| 35 | Gemma 4 31B gemma-4-31b-it multimodalvisionmulti-input reasoning | Google | 82.4 Value / Price | 53.0 | 41.8 | 0.0 | 0.0 | 82.4 | |
| 36 | Nemotron 3 Super (120B A12B) nemotron-3-super-120b-a12b codeprogrammingtool use | NVIDIA | 81.9 Value / Price | 43.5 | 41.8 | 7.2 | 22.2 | 81.9 | $0.085 in / $0.4 out |
| 37 | Step-3.5-Flash step-3.5-flash codeprogrammingtool use | StepFun | 81.9 Value / Price | 63.4 | 60.4 | 36.9 | 48.3 | 81.9 | $0.1 in / $0.4 out |
| 38 | Seed 2.0 Mini seed-2.0-mini multimodalvisionmulti-input reasoning | ByteDance | 80.2 Value / Price | 39.3 | 30.9 | 0.0 | 0.0 | 80.2 | $0.1 in / $0.4 out |
| 39 | Solar Mini 4 solar-mini4 codeprogrammingtool use | Upstage | 80.2 Value / Price | 0.0 | 58.2 | 0.0 | 48.7 | 80.2 | $0.1 in / $0.4 out |
| 40 | MiMo-V2.5 mimo-v2.5 multimodalvisionmulti-input reasoning | Xiaomi | 78.6 Value / Price | 47.2 | 85.2 | 0.0 | 28.0 | 78.6 | $0.168 in / $0.336 out |
21
Nemotron 3.5 Lightning (30B A3B)
NVIDIA
89.0
$0.08 in / $0.2 out
22
Laguna S 2.1
Poolside
88.2
$0.1 in / $0.2 out
23
Laguna XS 2.1
Poolside
88.2
$0.1 in / $0.2 out
24