Model comparison
GPT-4o mini vs Claude 3 Haiku
- Input
- $0.15 per 1M tokens
- Output
- $0.60 per 1M tokens
- Context
- 128K tokens
- Released
- 2024-07-18
- Input
- $0.25
- Output
- $1.25
- Context
- 200K tokens
- Released
- 2024-03-13
GPT-4o mini scores higher on 5 of the 5 benchmarks both models report; GPT-4o mini is cheaper on input tokens ($0.2 vs $0.3 per 1M, 1.7×); Claude 3 Haiku has the larger context window (200K vs 128K).
Specs and pricing side by side
| Spec | GPT-4o mini | Claude 3 Haiku |
|---|---|---|
| Maker | OpenAI | Anthropic |
| Released | 2024-07-18 | 2024-03-13 |
| Context window | 128K tokens | 200K tokens |
| Max output | 16,384 tokens | 4,096 tokens |
| Input price | $0.15 per 1M tokens | $0.25 |
| Output price | $0.60 per 1M tokens | $1.25 |
| Parameters | Not disclosed by OpenAI | Undisclosed |
| License | Proprietary (OpenAI commercial terms; available via API and ChatGPT) | Proprietary |
| Weights | API only | API onlysame |
| Modalities | text input, image input (vision), text output | Text, Vision |
| Knowledge cutoff | October 2023 | August 2023 |
Benchmarks both models report
| Benchmark | GPT-4o mini | Claude 3 Haiku |
|---|---|---|
| MMLU | 82% | 75.2% |
| MGSM | 87% | 71.7% |
| HumanEval | 87.2% | 75.9% |
| MATH | 70.2% | 38.9% |
| GPQA | 40.2% | 35.7% |
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 GPT-4o mini if…
- You care about MMLU, MGSM, HumanEval (it scores higher on 5 shared benchmarks).
- Cost matters: input tokens cost 1.7× less ($0.2 vs $0.3 per 1M).
- You need text input / image input (vision) / text output input, which Claude 3 Haiku lacks.
- Your use case is: high-volume text classification, tagging, and content moderation where cost per call matters.
Pick Claude 3 Haiku if…
- You need the longer context (200K vs 128K).
- You need Text / Vision input, which GPT-4o mini lacks.
- Your use case is: high-volume, cost-sensitive tasks like classification, tagging, and content moderation.
FAQ
Which is better, GPT-4o mini or Claude 3 Haiku?
GPT-4o mini scores higher on 5 of the 5 benchmarks both models report; GPT-4o mini is cheaper on input tokens ($0.2 vs $0.3 per 1M, 1.7×); Claude 3 Haiku has the larger context window (200K vs 128K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is GPT-4o mini?
GPT-4o mini: $0.15 per 1M tokens input, $0.60 per 1M tokens output. Claude 3 Haiku: $0.25 input, $1.25 output (list API prices as published by each maker).
What are the context windows of GPT-4o mini and Claude 3 Haiku?
GPT-4o mini offers 128K tokens with up to 16,384 tokens output; Claude 3 Haiku offers 200K tokens with up to 4,096 tokens output.
Is GPT-4o mini newer than Claude 3 Haiku?
GPT-4o mini was released 2024-07-18; Claude 3 Haiku was released 2024-03-13.