| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 1 | GPT-5.5 gpt-5.5 multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 74.3 | 96.4 | 55.3 | 48.5 | 3.3 | $5 in / $30 out |
| 2 | GPT-5.6 Luna gpt-5.6-luna multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 62.5 | 96.4 | 49.7 | 64.0 | 58.2 | |
| 3 | GPT-5.6 Sol gpt-5.6-sol multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 77.5 | 96.4 | 63.5 | 70.5 | 3.3 | |
| 4 | GPT-5.6 Terra gpt-5.6-terra multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 72.5 | 96.4 | 55.3 | 67.2 | 14.0 | |
| 5 | GPT-6.1 Sol gpt-6.1-sol multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 71.0 | 96.4 | 73.3 | 0.0 | 17.0 | $2 in / $10 out |
| 6 | GPT-6 Astra gpt-6-astra multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 74.8 | 96.4 | 74.6 | 0.0 | 1.1 | $10 in / $50 out |
| 7 | GPT-6 Luna gpt-6-luna multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 0.0 | 96.4 | 0.0 | 0.0 | 77.2 | $0.1 in / $0.5 out |
| 8 | GPT-6 Sol gpt-6-sol multimodalvisionmulti-input reasoning | OpenAI | 96.4 Inference | 0.0 | 96.4 | 0.0 | 0.0 | 17.0 | $2 in / $10 out |
| 9 | GPT-4.1 nano gpt-4.1-nano-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 87.5 Inference | 10.8 | 87.5 | 0.0 | 0.0 | 82.9 | |
| 10 | DeepSeek-V4.1-Flash deepseek-v4.1-flash multimodalvisionmulti-input reasoning | DeepSeek | 85.2 Inference | 57.2 | 85.2 | 0.0 | 0.0 | 67.6 | |
| 11 | DeepSeek-V4.1-Flash-1017 deepseek-v4.1-flash-1017 multimodalvisionmulti-input reasoning | DeepSeek | 85.2 Inference | 48.8 | 85.2 | 0.0 | 0.0 | 54.7 | |
| 12 | DeepSeek-V4-Flash-0423 deepseek-v4-flash-0423 codeprogrammingtool use | DeepSeek | 85.2 Inference | 51.4 | 85.2 | 23.7 | 40.7 | 90.4 | |
| 13 | DeepSeek-V4-Flash-0731 deepseek-v4-flash-0731 textinference | DeepSeek | 85.2 Inference | 0.0 | 85.2 | 56.7 | 0.0 | 93.1 | $0.06 in / $0.18 out |
| 14 | DeepSeek-V4-Flash-Max deepseek-v4-flash-max codeprogrammingtool use | DeepSeek | 85.2 Inference | 55.5 | 85.2 | 33.5 | 43.9 | 90.4 | |
| 15 | DeepSeek-V4-Flash-Vision-Exp deepseek-v4-flash-vision-exp multimodalvisionmulti-input reasoning | DeepSeek | 85.2 Inference | 0.0 | 85.2 | 0.0 | 0.0 | 50.5 | |
| 16 | DeepSeek-V4-Pro-0813 deepseek-v4-pro-0813 textinference | DeepSeek | 85.2 Inference | 67.6 | 85.2 | 68.2 | 0.0 | 35.4 | $1.3 in / $2.6 out |
| 17 | DeepSeek-V4-Pro-Max deepseek-v4-pro-max codeprogrammingtool use | DeepSeek | 85.2 Inference | 64.3 | 85.2 | 46.9 | 52.2 | 35.4 | |
| 18 | Gemini 2.5 Pro gemini-2.5-pro multimodalvisionmulti-input reasoning | Google | 85.2 Inference | 41.8 | 85.2 | 0.0 | 21.2 | 19.5 | |
| 19 | Gemini 3.1 Pro gemini-3.1-pro-preview multimodalvisionmulti-input reasoning | Google | 85.2 Inference | 70.6 | 85.2 | 46.7 | 61.7 | 14.0 | |
| 20 | Gemini 3.5 Flash gemini-3.5-flash multimodalvisionmulti-input reasoning | Google | 85.2 Inference | 57.6 | 85.2 | 59.8 | 22.9 | 20.9 |
1
GPT-5.5
OpenAI
96.4
$5 in / $30 out
2
GPT-5.6 Luna
OpenAI
96.4
$0.2 in / $1.2 out
3
GPT-5.6 Sol
OpenAI
96.4
$5 in / $30 out
4
Page 1 of 21 · 416 models