| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 81 | GPT-5.1 Medium gpt-5.1-medium-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 61.9 Inference | 63.6 | 61.9 | 0.0 | 0.0 | 28.9 | $1.25 in / $10 out |
| 82 | GPT-5 Medium gpt-5-medium-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 61.9 Inference | 56.7 | 61.9 | 0.0 | 0.0 | 28.9 | |
| 83 | Claude 3 Haiku claude-3-haiku-20240307 multimodalvisionmulti-input reasoning | Anthropic | 61.8 Inference | 5.8 | 61.8 | 0.0 | 0.0 | 57.9 | |
| 84 | Claude Haiku 4.5 claude-haiku-4-5-20251001 multimodalvisionmulti-input reasoning | Anthropic | 61.8 Inference | 32.7 | 61.8 | 54.2 | 56.6 | 37.7 | |
| 85 | o1-mini o1-mini textinference | OpenAI | 61.3 Inference | 25.7 | 61.3 | 0.0 | 0.0 | 30.1 | $3 in / $12 out |
| 86 | Llama 3.2 11B Instruct llama-3.2-11b-instruct multimodalvisionmulti-input reasoning | Meta | 60.3 Inference | 4.0 | 60.3 | 0.0 | 0.0 | 94.9 | $0.05 in / $0.05 out |
| 87 | MiMo-V2-Omni mimo-v2-omni multimodalvisionmulti-input reasoning | Xiaomi | 58.6 Inference | 0.0 | 58.6 | 0.0 | 54.4 | 44.8 | $0.4 in / $2 out |
| 88 | DeepSeek-V3.2 (Non-thinking) deepseek-chat textinference | DeepSeek | 58.0 Inference | 0.0 | 58.0 | 0.0 | 0.0 | 70.2 | $0.28 in / $0.42 out |
| 89 | DeepSeek-V3 deepseek-v3 codeprogrammingtool use | DeepSeek | 58.0 Inference | 27.3 | 58.0 | 0.0 | 10.4 | 60.5 | $0.27 in / $1.1 out |
| 90 | GPT OSS 120B High gpt-oss-120b-high multimodalvisionmulti-input reasoning | OpenAI | 58.0 Inference | 44.7 | 58.0 | 0.0 | 0.0 | 73.3 | |
| 91 | Gemini 1.0 Pro gemini-1.0-pro multimodalvisionmulti-input reasoning | Google | 57.2 Inference | 3.2 | 57.2 | 0.0 | 0.0 | 55.4 | |
| 92 | Llama 4 Maverick llama-4-maverick multimodalvisionmulti-input reasoning | Meta | 55.8 Inference | 35.4 | 55.8 | 0.0 | 0.0 | 57.1 | $0.17 in / $0.85 out |
| 93 | GPT-5.1 Thinking gpt-5.1-thinking-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 55.6 Inference | 64.9 | 55.6 | 0.0 | 56.2 | 27.0 | |
| 94 | Mistral Small 4 mistral-small-latest multimodalvisionmulti-input reasoning | Mistral AI | 55.2 Inference | 34.7 | 55.2 | 0.0 | 0.0 | 66.8 | |
| 95 | Qwen3-Coder qwen3-coder textinference | Alibaba Cloud / Qwen Team | 55.2 Inference | 0.0 | 55.2 | 0.0 | 0.0 | 88.5 | $0.18 in / $0.18 out |
| 96 | Qwen3 Max qwen3-max codeprogrammingtool use | Alibaba Cloud / Qwen Team | 55.2 Inference | 29.8 | 55.2 | 0.0 | 35.8 | 31.3 | $0.5 in / $5 out |
| 97 | GPT-4 gpt-4-0613 multimodalvisionmulti-input reasoning | OpenAI | 54.9 Inference | 6.8 | 54.9 | 0.0 | 0.0 | 18.7 | $30 in / $60 out |
| 98 | DeepSeek-V3.2 deepseek-v3.2 codeprogrammingtool use | DeepSeek | 53.2 Inference | 57.3 | 53.2 | 15.5 | 44.9 | 70.0 | $0.26 in / $0.38 out |
| 99 | GPT-4 Turbo gpt-4-turbo-2024-04-09 textinference | OpenAI | 52.7 Inference | 16.9 | 52.7 | 0.0 | 0.0 | 18.8 | $10 in / $30 out |
| 100 | GPT-5.3 Chat gpt-5.3-chat-latest multimodalvisionmulti-input reasoning | OpenAI | 52.7 Inference | 0.0 | 52.7 | 0.0 | 0.0 | 26.5 |
81
GPT-5.1 Medium
OpenAI
61.9
$1.25 in / $10 out
82
GPT-5 Medium
OpenAI
61.9
$1.25 in / $10 out
83
Claude 3 Haiku
Anthropic
61.8
$0.25 in / $1.25 out
84