Model comparison
Gemini 1.5 Flash vs Claude 3 Sonnet
- Input
- $0.075 per 1M tokens (prompts ≤128K tokens)
- Output
- $0.30 per 1M tokens (prompts ≤128K tokens)
- Context
- 1,048,576 tokens (1M)
- Released
- 2024-05-14
- Input
- $3.00
- Output
- $15.00
- Context
- 200K
- Released
- 2024-03-04
Claude 3 Sonnet scores higher on 3 of the 4 benchmarks both models report (the other leads on 1); Gemini 1.5 Flash is cheaper on input tokens ($0.1 vs $3 per 1M, 40×); Gemini 1.5 Flash has the larger context window (1.048576M vs 200K).
Specs and pricing side by side
| Spec | Gemini 1.5 Flash | Claude 3 Sonnet |
|---|---|---|
| Maker | Anthropic | |
| Released | 2024-05-14 | 2024-03-04 |
| Context window | 1,048,576 tokens (1M) | 200K |
| Max output | 8,192 tokens | 4K |
| Input price | $0.075 per 1M tokens (prompts ≤128K tokens) | $3.00 |
| Output price | $0.30 per 1M tokens (prompts ≤128K tokens) | $15.00 |
| Parameters | Not disclosed | not published |
| License | Proprietary | Proprietarysame |
| Weights | API only | API onlysame |
| Modalities | Text, Image, Audio, Video | Text, Vision |
| Knowledge cutoff | November 2023 | August 2023 |
Benchmarks both models report
| Benchmark | Gemini 1.5 Flash | Claude 3 Sonnet |
|---|---|---|
| MMLU | 78.9% | 79% |
| GPQA | 39.5% | 40.4% |
| GSM8K | 86.2% | 92.3% |
| HumanEval | 74.3% | 73% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Gemini 1.5 Flash if…
- You care about HumanEval (it scores higher on 1 shared benchmark).
- Cost matters: input tokens cost 40× less ($0.1 vs $3 per 1M).
- You need the longer context (1.048576M vs 200K).
- You need Image / Audio / Video input, which Claude 3 Sonnet lacks.
- Your use case is: summarizing long documents, transcripts, and multi-hour audio or video.
Pick Claude 3 Sonnet if…
- You care about MMLU, GPQA, GSM8K (it scores higher on 3 shared benchmarks).
- You need Vision input, which Gemini 1.5 Flash lacks.
- Your use case is: general-purpose text generation and summarization.
FAQ
Which is better, Gemini 1.5 Flash or Claude 3 Sonnet?
Claude 3 Sonnet scores higher on 3 of the 4 benchmarks both models report (the other leads on 1); Gemini 1.5 Flash is cheaper on input tokens ($0.1 vs $3 per 1M, 40×); Gemini 1.5 Flash has the larger context window (1.048576M vs 200K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Gemini 1.5 Flash?
Gemini 1.5 Flash: $0.075 per 1M tokens (prompts ≤128K tokens) input, $0.30 per 1M tokens (prompts ≤128K tokens) output. Claude 3 Sonnet: $3.00 input, $15.00 output (list API prices as published by each maker).
What are the context windows of Gemini 1.5 Flash and Claude 3 Sonnet?
Gemini 1.5 Flash offers 1,048,576 tokens (1M) with up to 8,192 tokens output; Claude 3 Sonnet offers 200K with up to 4K output.
Is Gemini 1.5 Flash newer than Claude 3 Sonnet?
Gemini 1.5 Flash was released 2024-05-14; Claude 3 Sonnet was released 2024-03-04.