Gemma 3 27B Instruct: Intelligence, Performance & Price Analysis
Analysis of Google's Gemma 3 27B Instruct 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:
Gemma 3 27B is of higher quality compared to average, with a MMLU score of 0.669 and a Intelligence Index across evaluations of 38.
Price:Speed:Gemma 3 27B is slower compared to average, with a output speed of 25.6 tokens per second.
Latency:Gemma 3 27B has a lower latency compared to average, taking 1.39s to receive the first token (TTFT).
Context Window:Gemma 3 27B has a smaller context windows than average, with a context window of 130k 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:
Comparisons to Gemma 3 27B
o1
GPT-4o (Nov '24)
GPT-4o mini
o3-mini (high)
GPT-4.5 (Preview)
Llama 3.3 Instruct 70B
Llama 3.1 Instruct 8B
Gemini 2.0 Pro Experimental (Feb '25)
Gemini 2.0 Flash (Feb '25)
Claude 3.5 Haiku
Claude 3.7 Sonnet (Extended Thinking)
Claude 3.7 Sonnet (Standard)
Mistral Large 2 (Nov '24)
Mistral Small 3
DeepSeek R1
DeepSeek V3
Grok 3 Reasoning Beta
Grok 3
Nova Pro
Nova Micro
Command A
QwQ 32B
Further details