| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Grok-4.20 Beta Non-Reasoning grok-4.20-beta-0309-non-reasoning multimodalvisionmulti-input reasoning | xAI | 97.2 Inference | 0.0 | 97.2 | 0.0 | 0.0 | 28.1 | $2 in / $6 out |
| 2 | Grok-4.20 Beta Reasoning grok-4.20-beta-0309-reasoning multimodalvisionmulti-input reasoning | xAI | 97.2 Inference | 0.0 | 97.2 | 0.0 | 0.0 | 28.1 | |
| 3 | Gemini 2.0 Flash gemini-2.0-flash multimodalvisionmulti-input reasoning | Google | 94.1 Inference | 33.4 | 94.1 | 0.0 | 0.0 | 82.7 | |
| 4 | GPT-4.1 nano gpt-4.1-nano-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 93.7 Inference | 12.6 | 93.7 | 0.0 | 0.0 | 83.0 | |
| 5 | Llama 4 Scout llama-4-scout multimodalvisionmulti-input reasoning | Meta | 93.0 Inference | 29.2 | 93.0 | 0.0 | 0.0 | 87.2 | $0.08 in / $0.3 out |
| 6 | Gemini 1.5 Flash gemini-1.5-flash multimodalvisionmulti-input reasoning | Google | 92.1 Inference | 23.2 | 92.1 | 0.0 | 0.0 | 71.9 | |
| 7 | Gemini 1.5 Flash 8B gemini-1.5-flash-8b multimodalvisionmulti-input reasoning | Google | 92.1 Inference | 10.4 | 92.1 | 0.0 | 0.0 | 88.3 | |
| 8 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 90.9 Inference | 20.8 | 90.9 | 8.9 | 2.6 | 56.8 | |
| 9 | GPT-5 mini gpt-5-mini-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 89.7 Inference | 41.9 | 89.7 | 0.0 | 23.7 | 56.3 | |
| 10 | Gemini 3.1 Flash-Lite gemini-3.1-flash-lite-preview multimodalvisionmulti-input reasoning | Google | 84.9 Inference | 56.3 | 84.9 | 0.0 | 0.0 | 50.6 | |
| 11 | Gemini 3 Flash gemini-3-flash-preview multimodalvisionmulti-input reasoning | Google | 84.9 Inference | 71.3 | 84.9 | 42.5 | 66.6 | 38.9 | |
| 12 | GPT-5.5 gpt-5.5 multimodalvisionmulti-input reasoning | OpenAI | 84.9 Inference | 80.3 | 84.9 | 76.2 | 65.4 | 6.7 | $5 in / $30 out |
| 13 | GPT-5.5 Pro gpt-5.5-pro multimodalvisionmulti-input reasoning | OpenAI | 84.9 Inference | 67.8 | 84.9 | 71.8 | 59.1 | 0.6 | $30 in / $180 out |
| 14 | MiMo-V2-Pro mimo-v2-pro codeprogrammingtool use | Xiaomi | 84.9 Inference | 0.0 | 84.9 | 0.0 | 66.6 | 36.4 | $1 in / $3 out |
| 15 | MiniMax M1 80K minimax-m1-80k codeprogrammingtool use | MiniMax | 84.9 Inference | 24.6 | 84.9 | 20.9 | 19.4 | 41.7 | $0.55 in / $2.2 out |
| 16 | Ministral 3 (8B Reasoning 2512) ministral-8b-latest multimodalvisionmulti-input reasoning | Mistral AI | 84.8 Inference | 31.8 | 84.8 | 0.0 | 0.0 | 92.1 | |
| 17 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 83.8 Inference | 24.7 | 83.8 | 29.5 | 25.3 | 83.3 | $0.1 in / $0.4 out |
| 18 | MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use | Xiaomi | 79.8 Inference | 53.7 | 79.8 | 27.2 | 39.3 | 85.9 | $0.1 in / $0.3 out |
| 19 | Min istral 3 (3B Reasoning 2512) ministral-3b-latest multimodalvisionmulti-input reasoning | Mistral AI | 79.7 Inference | 22.1 | 79.7 | 0.0 | 0.0 | 95.8 | |
| 20 | GPT-5.4 Mini gpt-5.4-mini texttext-to-textlanguage | OpenAI | 77.4 Inference | 57.4 | 77.4 | 27.1 | 26.9 | 32.8 |
1
Grok-4.20 Beta Non-Reasoning
xAI
97.2
$2 in / $6 out
2
Grok-4.20 Beta Reasoning
xAI
97.2
$2 in / $6 out
3Google
Gemini 2.0 Flash
94.1
$0.1 in / $0.4 out
Page 1 of 15 · 294 models