| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | GPT-5.4 nano gpt-5.4-nano multimodalvisionmulti-input reasoning | OpenAI | 77.4 Inference | 46.1 | 77.4 | 11.0 | 11.2 | 57.2 | $0.2 in / $1.25 out |
| 22 | GPT OSS 20B gpt-oss-20b textinference | OpenAI | 77.3 Inference | 26.1 | 77.3 | 6.0 | 0.0 | 79.3 | $0.1 in / $0.5 out |
| 23 | Ministral 3 (14B Reasoning 2512) ministral-14b-latest multimodalvisionmulti-input reasoning | Mistral AI | 76.8 Inference | 37.9 | 76.8 | 0.0 | 0.0 | 84.5 | |
| 24 | GPT-4.1 gpt-4.1-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 75.4 Inference | 28.8 | 75.4 | 32.8 | 17.7 | 34.6 | |
| 25 | MiniMax M2.1 minimax-m2.1 codeprogrammingtool use | MiniMax | 73.9 Inference | 42.7 | 73.9 | 56.6 | 50.6 | 57.7 | $0.3 in / $1.2 out |
| 26 | MiniMax M2.5 minimax-m2.5 codeprogrammingtool use | MiniMax | 73.9 Inference | 0.0 | 73.9 | 53.0 | 56.3 | 57.7 | $0.3 in / $1.2 out |
| 27 | Mercury 2 mercury-2 codeprogrammingtool use | Inception | 72.5 Inference | 44.6 | 72.5 | 0.0 | 22.3 | 69.2 | $0.25 in / $0.75 out |
| 28 | GPT-5.1 gpt-5.1-2025-11-13 multimodalvisionmulti-input reasoning | OpenAI | 71.4 Inference | 65.0 | 71.4 | 0.0 | 57.2 | 31.9 | |
| 29 | GPT-5.1 Instant gpt-5.1-instant-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 71.4 Inference | 65.0 | 71.4 | 0.0 | 57.2 | 31.9 | |
| 30 | GPT-5.2 gpt-5.2-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 71.4 Inference | 76.9 | 71.4 | 50.3 | 72.4 | 26.4 | |
| 31 | Qwen2.5 7B Instruct qwen-2.5-7b-instruct textinference | Alibaba Cloud / Qwen Team | 70.8 Inference | 7.5 | 70.8 | 0.0 | 0.0 | 77.3 | $0.3 in / $0.3 out |
| 32 | o3-mini o3-mini codeprogrammingtool use | OpenAI | 70.7 Inference | 26.0 | 70.7 | 11.9 | 12.5 | 41.9 | $1.1 in / $4.4 out |
| 33 | o4-mini o4-mini multimodalvisionmulti-input reasoning | OpenAI | 70.7 Inference | 48.8 | 70.7 | 38.2 | 32.7 | 41.9 | $1.1 in / $4.4 out |
| 34 | Nova Lite nova-lite multimodalvisionmulti-input reasoning | Amazon | 69.9 Inference | 13.6 | 69.9 | 0.0 | 0.0 | 86.4 | $0.06 in / $0.24 out |
| 35 | Nova Pro nova-pro multimodalvisionmulti-input reasoning | Amazon | 69.9 Inference | 20.0 | 69.9 | 0.0 | 0.0 | 42.8 | $0.8 in / $3.2 out |
| 36 | Llama 3.2 3B Instruct llama-3.2-3b-instruct textinference | Meta | 69.0 Inference | 5.3 | 69.0 | 0.0 | 0.0 | 98.8 | $0.01 in / $0.02 out |
| 37 | Claude 3.5 Haiku claude-3-5-haiku-20241022 codeprogrammingtool use | Anthropic | 68.7 Inference | 10.9 | 68.7 | 3.0 | 7.9 | 43.1 | |
| 38 | Claude 3 Haiku claude-3-haiku-20240307 multimodalvisionmulti-input reasoning | Anthropic | 68.7 Inference | 5.8 | 68.7 | 0.0 | 0.0 | 59.9 | |
| 39 | Grok-4.1 Fast Non-Reasoning grok-4-1-fast-non-reasoning multimodalvisionmulti-input reasoning | xAI | 68.2 Inference | 0.0 | 68.2 | 0.0 | 0.0 | 67.2 | |
| 40 | Grok-4.1 Fast Reasoning grok-4-1-fast-reasoning multimodalvisionmulti-input reasoning | xAI | 68.2 Inference | 0.0 | 68.2 | 0.0 | 0.0 | 67.2 |
21
GPT-5.4 nano
OpenAI
77.4
$0.2 in / $1.25 out
22
GPT OSS 20B
OpenAI
77.3
$0.1 in / $0.5 out
23
Ministral 3 (14B Reasoning 2512)
Mistral AI
76.8
$0.2 in / $0.2 out
24