| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 81 | DeepSeek-V3.2 (Thinking) deepseek-reasoner codeprogrammingtool use | DeepSeek | 15.0 Agentic | 51.8 | 0.0 | 15.0 | 43.5 | 0.0 | N/A |
| 82 | DeepSeek-V3.2 deepseek-v3.2 codeprogrammingtool use | DeepSeek | 15.0 Agentic | 56.7 | 0.0 | 15.0 | 43.5 | 0.0 | N/A |
| 83 | GPT-4o gpt-4o-2024-08-06 multimodalvisionmulti-input reasoning | OpenAI | 14.9 Agentic | 30.4 | 39.4 | 14.9 | 4.0 | 26.8 | |
| 84 | DeepSeek-V3.1 deepseek-v3.1 codeprogrammingtool use | DeepSeek | 14.0 Agentic | 37.5 | 0.0 | 14.0 | 26.4 | 0.0 | N/A |
| 85 | Grok 4 Fast grok-4-fast multimodalvisionmulti-input reasoning | xAI | 13.7 Agentic | 57.1 | 62.1 | 13.7 | 0.0 | 73.7 | $0.2 in / $0.5 out |
| 86 | Kimi K2 Instruct kimi-k2-instruct codeprogrammingtool use | Moonshot AI | 13.5 Agentic | 23.8 | 0.0 | 13.5 | 14.0 | 0.0 | N/A |
| 87 | Qwen3.6-35B-A3B qwen3.6-35b-a3b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 13.5 Agentic | 54.2 | 0.0 | 13.5 | 25.1 | 0.0 | N/A |
| 88 | Nova 2 Lite nova-2-lite multimodalvisionmulti-input reasoning | Amazon | 13.0 Agentic | 42.8 | 72.2 | 13.0 | 27.0 | 50.0 | $0.3 in / $2.5 out |
| 89 | o3-mini o3-mini codeprogrammingtool use | OpenAI | 11.9 Agentic | 26.8 | 0.0 | 11.9 | 12.9 | 0.0 | N/A |
| 90 | GLM-4.7-Flash glm-4.7-flash codeprogrammingtool use | Zhipu AI | 10.7 Agentic | 37.1 | 0.0 | 10.7 | 19.0 | 0.0 | N/A |
| 91 | GPT-5.4 nano gpt-5.4-nano multimodalvisionmulti-input reasoning | OpenAI | 10.4 Agentic | 46.0 | 56.3 | 10.4 | 10.7 | 70.9 | $0.2 in / $1.25 out |
| 92 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 8.9 Agentic | 20.2 | 87.8 | 8.9 | 2.4 | 65.6 | |
| 93 | Nemotron 3 Super (120B A12B) nemotron-3-super-120b-a12b codeprogrammingtool use | NVIDIA | 8.1 Agentic | 47.3 | 0.0 | 8.1 | 24.5 | 0.0 | N/A |
| 94 | DeepSeek-V3.2-Speciale deepseek-v3.2-speciale codeprogrammingtool use | DeepSeek | 7.6 Agentic | 53.0 | 0.0 | 7.6 | 43.5 | 0.0 | |
| 95 | Sarvam-30B sarvam-30b codeprogrammingtool use | Sarvam AI | 7.6 Agentic | 45.7 | 0.0 | 7.6 | 4.7 | 0.0 | N/A |
| 96 | GPT OSS 20B gpt-oss-20b textinference | OpenAI | 6.0 Agentic | 24.8 | 0.0 | 6.0 | 0.0 | 0.0 | N/A |
| 97 | Kimi K2-Instruct-0905 kimi-k2-instruct-0905 codeprogrammingtool use | Moonshot AI | 6.0 Agentic | 23.8 | 0.0 | 6.0 | 18.1 | 0.0 | |
| 98 | Qwen2.5 VL 72B Instruct qwen2.5-vl-72b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 5.6 Agentic | 24.1 | 0.0 | 5.6 | 0.0 | 0.0 | N/A |
| 99 | Claude 3.5 Haiku claude-3-5-haiku-20241022 codeprogrammingtool use | Anthropic | 3.0 Agentic | 10.5 | 0.0 | 3.0 | 7.1 | 0.0 | |
| 100 | Nemotron 3 Nano (30B A3B) nemotron-3-nano-30b-a3b codeprogrammingtool use | NVIDIA | 3.0 Agentic | 44.5 | 41.1 | 3.0 | 4.0 | 100.0 | $0.06 in / $0.24 out |
81
DeepSeek-V3.2 (Thinking)
DeepSeek
15.0
N/A
82
DeepSeek-V3.2
DeepSeek
15.0
N/A
83
GPT-4o
OpenAI
14.9
$2.5 in / $10 out
84