| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 81 | Grok 4 Fast grok-4-fast multimodalvisionmulti-input reasoning | xAI | 14.7 Agentic | 57.6 | 68.8 | 14.7 | 0.0 | 67.2 | $0.2 in / $0.5 out |
| 82 | o3-mini o3-mini codeprogrammingtool use | OpenAI | 11.9 Agentic | 25.6 | 70.4 | 11.9 | 12.2 | 41.6 | $1.1 in / $4.4 out |
| 83 | GLM-4.7-Flash glm-4.7-flash codeprogrammingtool use | Zhipu AI | 11.4 Agentic | 38.2 | 29.7 | 11.4 | 20.7 | 72.1 | $0.07 in / $0.4 out |
| 84 | GPT-5.4 nano gpt-5.4-nano multimodalvisionmulti-input reasoning | OpenAI | 9.7 Agentic | 45.6 | 76.5 | 9.7 | 10.0 | 57.1 | $0.2 in / $1.25 out |
| 85 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 8.9 Agentic | 20.7 | 90.6 | 8.9 | 2.6 | 56.8 | |
| 86 | Nemotron 3 Super (120B A12B) nemotron-3-super-120b-a12b codeprogrammingtool use | NVIDIA | 8.7 Agentic | 48.3 | 0.0 | 8.7 | 26.8 | 0.0 | N/A |
| 87 | DeepSeek-V3.2-Speciale deepseek-v3.2-speciale codeprogrammingtool use | DeepSeek | 8.5 Agentic | 53.8 | 0.0 | 8.5 | 44.9 | 0.0 | |
| 88 | Sarvam-30B sarvam-30b codeprogrammingtool use | Sarvam AI | 8.2 Agentic | 46.4 | 0.0 | 8.2 | 5.2 | 0.0 | N/A |
| 89 | Kimi K2-Instruct-0905 kimi-k2-instruct-0905 codeprogrammingtool use | Moonshot AI | 6.6 Agentic | 24.4 | 0.0 | 6.6 | 19.3 | 0.0 | |
| 90 | GPT OSS 20B gpt-oss-20b textinference | OpenAI | 6.0 Agentic | 25.8 | 77.2 | 6.0 | 0.0 | 79.0 | $0.1 in / $0.5 out |
| 91 | Qwen2.5 VL 72B Instruct qwen2.5-vl-72b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 5.7 Agentic | 24.9 | 0.0 | 5.7 | 0.0 | 0.0 | N/A |
| 92 | Nemotron 3 Nano (30B A3B) nemotron-3-nano-30b-a3b codeprogrammingtool use | NVIDIA | 3.3 Agentic | 45.4 | 66.0 | 3.3 | 4.4 | 90.9 | $0.06 in / $0.24 out |
| 93 | Claude 3.5 Haiku claude-3-5-haiku-20241022 codeprogrammingtool use | Anthropic | 3.0 Agentic | 10.8 | 30.5 | 3.0 | 7.8 | 31.8 | |
| 94 | Qwen2.5 VL 32B Instruct qwen2.5-vl-32b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 1.6 Agentic | 21.2 | 0.0 | 1.6 | 0.0 | 0.0 | N/A |
| 95 | ChatGPT-4o Latest chatgpt-4o-latest multimodalvisionmulti-input reasoning | OpenAI | 0.0 Agentic | 56.0 | 63.8 | 0.0 | 0.0 | 32.0 | |
| 96 | Claude 3.5 Sonnet claude-3-5-sonnet-20240620 multimodalvisionmulti-input reasoning | Anthropic | 0.0 Agentic | 25.4 | 68.2 | 0.0 | 0.0 | 24.6 | |
| 97 | Claude 3 Haiku claude-3-haiku-20240307 multimodalvisionmulti-input reasoning | Anthropic | 0.0 Agentic | 5.8 | 61.8 | 0.0 | 0.0 | 57.9 | |
| 98 | Claude 3 Opus claude-3-opus-20240229 multimodalvisionmulti-input reasoning | Anthropic | 0.0 Agentic | 19.3 | 71.7 | 0.0 | 0.0 | 19.5 | |
| 99 | Claude 3 Sonnet claude-3-sonnet-20240229 multimodalvisionmulti-input reasoning | Anthropic | 0.0 Agentic | 10.0 | 30.5 | 0.0 | 0.0 | 13.3 | |
| 100 | Codestral-22B codestral-22b textinference | Mistral AI | 0.0 Agentic | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
81
Grok 4 Fast
xAI
14.7
$0.2 in / $0.5 out
82
o3-mini
OpenAI
11.9
$1.1 in / $4.4 out
83
GLM-4.7-Flash
Zhipu AI
11.4
$0.07 in / $0.4 out
84