| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | GPT-5.1 High gpt-5.1-high-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 67.1 Benchmarks | 67.1 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 22 | Muse Spark muse-spark multimodalvisionmulti-input reasoning | Meta | 67.1 Benchmarks | 67.1 | 0.0 | 64.4 | 36.2 | 0.0 | N/A |
| 23 | Qwen3.6 Plus qwen3.6-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 66.9 Benchmarks | 66.9 | 62.8 | 33.6 | 52.8 | 54.9 | $0.5 in / $3 out |
| 24 | Seed 2.0 Pro seed-2.0-pro multimodalvisionmulti-input reasoning | ByteDance | 66.8 Benchmarks | 66.8 | 23.2 | 44.8 | 56.0 | 54.9 | $0.5 in / $3 out |
| 25 | Seed 2.1 Turbo seed-2.1-turbo multimodalvisionmulti-input reasoning | ByteDance | 66.3 Benchmarks | 66.3 | 0.0 | 63.1 | 53.8 | 0.0 | N/A |
| 26 | Kimi K2-Thinking-0905 kimi-k2-thinking-0905 codeprogrammingtool use | Moonshot AI | 66.2 Benchmarks | 66.2 | 0.0 | 50.8 | 58.0 | 0.0 | |
| 27 | Hy3 hy3 codeprogrammingtool use | Tencent | 65.9 Benchmarks | 65.9 | 0.0 | 40.4 | 59.2 | 0.0 | N/A |
| 28 | DeepSeek-V4-Pro-Max deepseek-v4-pro-max codeprogrammingtool use | DeepSeek | 64.9 Benchmarks | 64.9 | 84.8 | 51.0 | 52.0 | 45.1 | |
| 29 | Qwen3.7 Max qwen3.7-max multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 64.7 Benchmarks | 64.7 | 62.8 | 49.6 | 74.2 | 43.9 | $1.25 in / $3.75 out |
| 30 | GPT-5.2 Pro gpt-5.2-pro-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 64.4 Benchmarks | 64.4 | 0.0 | 46.1 | 0.0 | 0.0 | |
| 31 | GPT-5.1 Medium gpt-5.1-medium-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 64.1 Benchmarks | 64.1 | 44.9 | 0.0 | 0.0 | 32.0 | |
| 32 | GPT-5.6 Luna gpt-5.6-luna multimodalvisionmulti-input reasoning | OpenAI | 63.9 Benchmarks | 63.9 | 94.5 | 55.0 | 65.5 | 37.8 | |
| 33 | Kimi K2.5 kimi-k2.5 multimodalvisionmulti-input reasoning | Moonshot AI | 63.7 Benchmarks | 63.7 | 0.0 | 41.0 | 41.8 | 0.0 | N/A |
| 34 | Kimi K2.6 kimi-k2.6 texttext-to-textlanguage | Moonshot AI | 63.5 Benchmarks | 63.5 | 32.9 | 47.2 | 69.4 | 46.3 | |
| 35 | Qwen3.7-Plus qwen3.7-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 62.9 Benchmarks | 62.9 | 62.8 | 48.1 | 61.1 | 69.5 | $0.32 in / $1.28 out |
| 36 | Step-3.5-Flash step-3.5-flash codeprogrammingtool use | StepFun | 62.8 Benchmarks | 62.8 | 59.8 | 36.5 | 48.6 | 93.9 | $0.1 in / $0.4 out |
| 37 | GLM-5.1 glm-5.1 codeprogrammingtool use | Zhipu AI | 62.6 Benchmarks | 62.6 | 15.9 | 35.2 | 47.2 | 40.2 | $1.4 in / $4.4 out |
| 38 | GPT-5.1 gpt-5.1-2025-11-13 multimodalvisionmulti-input reasoning | OpenAI | 62.4 Benchmarks | 62.4 | 62.8 | 0.0 | 51.4 | 37.3 | |
| 39 | GPT-5.1 Instant gpt-5.1-instant-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 62.4 Benchmarks | 62.4 | 62.8 | 0.0 | 51.4 | 37.3 | |
| 40 | GPT-5.1 Thinking gpt-5.1-thinking-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 62.4 Benchmarks | 62.4 | 0.0 | 0.0 | 51.4 | 0.0 |
21
GPT-5.1 High
OpenAI
67.1
N/A
22
Muse Spark
Meta
67.1
N/A
23
Qwen3.6 Plus
Alibaba Cloud / Qwen Team
66.9
$0.5 in / $3 out
24