+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Devstral Small 1.1 vs Phi-3.5-vision-instruct
Comprehensive side-by-side LLM comparison
Phi-3.5-vision-instruct leads with 56.1% higher average benchmark score. Phi-3.5-vision-instruct supports multimodal inputs. Overall, Phi-3.5-vision-instruct is the stronger choice for coding tasks.
+
+
+
+
Mistral AI
Devstral Small 1.1 is a language model developed by Mistral AI. The model shows competitive results across 1 benchmarks. Notable strengths include SWE-Bench Verified (53.6%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents Mistral AI's latest advancement in AI technology.
+
+
+
+
Microsoft
Phi-3.5-vision-instruct is a multimodal language model developed by Microsoft. It achieves strong performance with an average score of 68.3% across 9 benchmarks. It excels particularly in ScienceQA (91.3%), POPE (86.1%), MMBench (81.9%). As a multimodal model, it can process and understand text, images, and other input formats seamlessly. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Microsoft's latest advancement in AI technology.
10 months newer
Phi-3.5-vision-instruct
Microsoft
2024-08-23
Devstral Small 1.1
Mistral AI
2025-07-11
Performance Metrics
Context window and performance specifications
Average performance across 10 common benchmarks
+
+
+
+
Devstral Small 1.1
Average Score:5.4%
+
+
+
+
Phi-3.5-vision-instruct
Average Score:61.4%(+56.1%)
Provider Availability & Performance
Available providers and their performance metrics
+
+
+
+
Devstral Small 1.1
1 providers
Mistral AI
Throughput: 137.1 tok/s
Latency: 0.23ms
+
+
+
+
Phi-3.5-vision-instruct
+
+
+
+
Devstral Small 1.1
Avg Score:5.4%
Providers:1
+
+
+
+
Phi-3.5-vision-instruct
Avg Score:61.4%(+56.1%)
Providers:0