Qwen3 4B: Intelligence, Performance & Price Analysis
Analysis of Alibaba's Qwen3 4B and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Comparison Summary
Intelligence:
Qwen3 4B is of lower quality compared to average, with a MMLU score of 0.586 and a Intelligence Index across evaluations of 35.
Price:Qwen3 4B is cheaper compared to average with a price of $0.19 per 1M Tokens (blended 3:1).
Qwen3 4B Input token price: $0.11, Output token price: $0.42 per 1M Tokens.
Speed:Qwen3 4B Input token price: $0.11, Output token price: $0.42 per 1M Tokens.
Qwen3 4B is slower compared to average, with a output speed of 102.6 tokens per second.
Latency:Qwen3 4B has a lower latency compared to average, taking 0.98s to receive the first token (TTFT).
Context Window:Qwen3 4B has a smaller context windows than average, with a context window of 32k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Qwen3 4B Model Details
Comparisons to Qwen3 4B
o4-mini (high)
o3
GPT-4.1
Llama 4 Maverick
Llama 4 Scout
Gemini 2.5 Pro Preview (May' 25)
Gemini 2.5 Flash Preview (May '25) (Reasoning)
Claude 4 Sonnet (Extended Thinking)
Claude 4 Sonnet
Claude 3.7 Sonnet (Extended Thinking)
Mistral Medium 3
DeepSeek V3 0324 (March '25)
DeepSeek R1 0528 (May '25)
Grok 3 mini Reasoning (high)
Nova Premier
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
Qwen3 235B A22B (Reasoning)
GPT-4o (Nov '24)
DeepSeek R1 (Jan '25)
Further details