| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | GLM-5.3 glm-5.3 textinference | Zhipu AI | 60.2 Agentic | 68.9 | 85.2 | 60.2 | 0.0 | 29.7 | $1.2 in / $4 out |
| 22 | Gemini 3.5 Flash gemini-3.5-flash multimodalvisionmulti-input reasoning | Google | 59.8 Agentic | 57.6 | 85.2 | 59.8 | 22.9 | 20.9 | |
| 23 | Muse Spark muse-spark multimodalvisionmulti-input reasoning | Meta | 59.5 Agentic | 66.0 | 0.0 | 59.5 | 39.0 | 0.0 | N/A |
| 24 | Seed 2.1 Turbo seed-2.1-turbo multimodalvisionmulti-input reasoning | ByteDance | 58.5 Agentic | 64.1 | 0.0 | 58.5 | 53.4 | 0.0 | N/A |
| 25 | Claude Opus 4 claude-opus-4-20250514 multimodalvisionmulti-input reasoning | Anthropic | 57.4 Agentic | 35.8 | 0.0 | 57.4 | 46.7 | 0.0 | |
| 26 | Nova 2 Pro nova-2-pro multimodalvisionmulti-input reasoning | Amazon | 57.2 Agentic | 43.7 | 0.0 | 57.2 | 48.6 | 0.0 | N/A |
| 27 | DeepSeek-V4-Flash-0731 deepseek-v4-flash-0731 textinference | DeepSeek | 56.7 Agentic | 0.0 | 85.2 | 56.7 | 0.0 | 93.1 | $0.06 in / $0.18 out |
| 28 | GPT-5.5 gpt-5.5 multimodalvisionmulti-input reasoning | OpenAI | 55.3 Agentic | 74.3 | 96.4 | 55.3 | 48.5 | 3.3 | $5 in / $30 out |
| 29 | GPT-5.6 Terra gpt-5.6-terra multimodalvisionmulti-input reasoning | OpenAI | 55.3 Agentic | 72.5 | 96.4 | 55.3 | 67.2 | 14.0 | |
| 30 | Inkling-Small inkling-small multimodalvisionmulti-input reasoning | Thinking Machines Lab | 55.0 Agentic | 47.5 | 58.2 | 55.0 | 57.9 | 54.7 | $0.3 in / $1.2 out |
| 31 | Claude Sonnet 5 claude-sonnet-5 multimodalvisionmulti-input reasoning | Anthropic | 54.3 Agentic | 64.7 | 28.2 | 54.3 | 73.8 | 15.4 | |
| 32 | Claude Opus 4.7 claude-opus-4-7 multimodalvisionmulti-input reasoning | Anthropic | 53.9 Agentic | 74.6 | 28.2 | 53.9 | 75.6 | 6.2 | |
| 33 | Gemini 3 Pro gemini-3-pro-preview multimodalvisionmulti-input reasoning | Google | 51.0 Agentic | 69.4 | 0.0 | 51.0 | 52.8 | 0.0 | |
| 34 | Kimi K2-Thinking-0905 kimi-k2-thinking-0905 codeprogrammingtool use | Moonshot AI | 50.7 Agentic | 64.8 | 0.0 | 50.7 | 57.9 | 0.0 | |
| 35 | Qwen3-Coder 480B A35B Instruct qwen3-coder-480b-a35b-instruct codeprogrammingtool use | Alibaba Cloud / Qwen Team | 50.7 Agentic | 0.0 | 41.8 | 50.7 | 30.6 | 61.5 | |
| 36 | GLM-5V-Turbo glm-5v-turbo multimodalvisionmulti-input reasoning | Zhipu AI | 50.2 Agentic | 0.0 | 0.0 | 50.2 | 0.0 | 0.0 | N/A |
| 37 | Claude Haiku 4.5 claude-haiku-4-5-20251001 multimodalvisionmulti-input reasoning | Anthropic | 49.8 Agentic | 30.1 | 51.8 | 49.8 | 54.1 | 34.2 | |
| 38 | GPT-5.6 Luna gpt-5.6-luna multimodalvisionmulti-input reasoning | OpenAI | 49.7 Agentic | 62.5 | 96.4 | 49.7 | 64.0 | 58.2 | $0.2 in / $1.2 out |
| 39 | Muse Glimmer-30B muse-glimmer-30b multimodalvisionmulti-input reasoning | Meta | 49.7 Agentic | 42.2 | 15.0 | 49.7 | 38.6 | 54.7 | $0.3 in / $1.2 out |
| 40 | Claude Opus 4.6 claude-opus-4-6 multimodalvisionmulti-input reasoning | Anthropic | 49.5 Agentic | 72.7 | 28.2 | 49.5 | 71.4 | 6.2 |
21
GLM-5.3
Zhipu AI
60.2
$1.2 in / $4 out
22Google
Gemini 3.5 Flash
59.8
$1.5 in / $9 out
23
Muse Spark
Meta
59.5
N/A
24