| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | GLM-5.3 glm-5.3 textinference | Zhipu AI | 68.9 Benchmarks | 68.9 | 85.2 | 60.2 | 0.0 | 29.7 | $1.2 in / $4 out |
| 22 | Grok-4 Heavy grok-4-heavy multimodalvisionmulti-input reasoning | xAI | 68.2 Benchmarks | 68.2 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 23 | DeepSeek-V4-Pro-0813 deepseek-v4-pro-0813 textinference | DeepSeek | 67.6 Benchmarks | 67.6 | 85.2 | 68.2 | 0.0 | 35.4 | $1.3 in / $2.6 out |
| 24 | Gemini 3 Flash gemini-3-flash-preview multimodalvisionmulti-input reasoning | Google | 67.5 Benchmarks | 67.5 | 66.7 | 28.2 | 61.8 | 38.2 | |
| 25 | Hy4 preview hy4-preview codeprogrammingtool use | Tencent | 67.4 Benchmarks | 67.4 | 0.0 | 68.3 | 68.6 | 0.0 | N/A |
| 26 | Seed 2.1 Pro seed-2.1-pro multimodalvisionmulti-input reasoning | ByteDance | 67.4 Benchmarks | 67.4 | 0.0 | 67.9 | 58.6 | 0.0 | N/A |
| 27 | GLM-5.2 glm-5.2 codeprogrammingtool use | Zhipu AI | 67.2 Benchmarks | 67.2 | 85.2 | 39.9 | 55.9 | 40.7 | $0.75 in / $2.4 out |
| 28 | Muse Spark 1.1 muse-spark-1.1 multimodalvisionmulti-input reasoning | Meta | 66.9 Benchmarks | 66.9 | 85.2 | 74.6 | 53.4 | 27.7 | $1.25 in / $4.25 out |
| 29 | Muse Spark muse-spark multimodalvisionmulti-input reasoning | Meta | 66.0 Benchmarks | 66.0 | 0.0 | 59.5 | 39.0 | 0.0 | N/A |
| 30 | GPT-5.1 High gpt-5.1-high-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 65.9 Benchmarks | 65.9 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 31 | Gemini 3.7 Flash gemini-3.7-flash multimodalvisionmulti-input reasoning | Google | 65.8 Benchmarks | 65.8 | 85.2 | 0.0 | 0.0 | 32.7 | |
| 32 | Seed 2.0 Pro seed-2.0-pro multimodalvisionmulti-input reasoning | ByteDance | 65.6 Benchmarks | 65.6 | 30.9 | 45.0 | 56.0 | 38.2 | $0.5 in / $3 out |
| 33 | Qwen3.6 Plus qwen3.6-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 65.4 Benchmarks | 65.4 | 66.7 | 29.9 | 53.6 | 38.2 | $0.5 in / $3 out |
| 34 | Kimi K2-Thinking-0905 kimi-k2-thinking-0905 codeprogrammingtool use | Moonshot AI | 64.8 Benchmarks | 64.8 | 0.0 | 50.7 | 57.9 | 0.0 | |
| 35 | Claude Sonnet 5 claude-sonnet-5 multimodalvisionmulti-input reasoning | Anthropic | 64.7 Benchmarks | 64.7 | 28.2 | 54.3 | 73.8 | 15.4 | |
| 36 | Hy3 hy3 codeprogrammingtool use | Tencent | 64.7 Benchmarks | 64.7 | 41.8 | 37.8 | 57.9 | 72.0 | $0.14 in / $0.58 out |
| 37 | GPT-5.1 Medium gpt-5.1-medium-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 64.6 Benchmarks | 64.6 | 45.7 | 0.0 | 0.0 | 24.1 | |
| 38 | GLM-5.3-Flash glm-5.3-flash multimodalvisionmulti-input reasoning | Zhipu AI | 64.5 Benchmarks | 64.5 | 85.2 | 72.6 | 0.0 | 74.7 | $0.15 in / $0.5 out |
| 39 | Qwen3.7 Max qwen3.7-max multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 64.4 Benchmarks | 64.4 | 66.7 | 48.6 | 72.6 | 30.5 | $1.25 in / $3.75 out |
| 40 | DeepSeek-V4-Pro-Max deepseek-v4-pro-max codeprogrammingtool use | DeepSeek | 64.3 Benchmarks | 64.3 | 85.2 | 46.9 | 52.2 | 35.4 |
21
GLM-5.3
Zhipu AI
68.9
$1.2 in / $4 out
22
Grok-4 Heavy
xAI
68.2
N/A
23
DeepSeek-V4-Pro-0813
DeepSeek
67.6
$1.3 in / $2.6 out
24