Model comparison
Claude 3 Haiku vs GPT-4
Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.
Anthropic
Claude 3 Haiku
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance.
OpenAI
GPT-4
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader.
Quick take
Where each one leads
- GPT-4 scores higher on the Artificial Analysis Intelligence Index: 6.7 to 5.6.
Each line comes from a checked value in the tables below. Pick on your workload: price and usage matter for high volume, context and scores for long documents and agent loops.
Price history
Prices side by side, day by day
- Claude 3 Haiku No price history checked yet
- GPT-4
- Claude 3 Haiku No price history checked yet
- GPT-4
Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.
Price
What each one costs now
| Measure | Claude 3 Haiku | GPT-4 |
|---|---|---|
| Input price | Not checked yet | $30.00 per million tokens |
| Output price | Not checked yet | $60.00 per million tokens |
Scores
Benchmarks, with source and date
| Measure | Claude 3 Haiku | GPT-4 |
|---|---|---|
| Artificial Analysis Intelligence Index | 5.6 | 6.7 Leads |
| Artificial Analysis Coding Index | Not checked yet | 13.1 |
| LMArena text rating (Elo) | 1,195 | 1,206 Leads |
| LMArena vision rating (Elo) | 950 | Not checked yet |
Specs
Context, modalities and tool use
| Measure | Claude 3 Haiku | GPT-4 |
|---|---|---|
| Context window | Not checked yet | 8,191 tokens |
| Reads | Not checked yet | Text |
| Writes | Not checked yet | Text |
| Tool calling | Not checked yet | Yes |
| Reasoning mode | Not checked yet | No |
| Open weights | Not checked yet | No |
| Listed since | Not checked yet | 28 May 2023 |
Usage
How much each one is used
| Measure | Claude 3 Haiku | GPT-4 |
|---|---|---|
| Tokens served on OpenRouter in a day | 3.9M (for 26 Sept 2026) | 4.6M (for 10 Nov 2026) |
| Requests on OpenRouter in a day | 1.1K (for 26 Sept 2026) | 4.6K (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | 81 (for 26 Sept 2026) | 195 (for 10 Nov 2026) |
| Token usage, last 7 days | Not checked yet | Up 144% on the week before (for 10 Nov 2026) |
- Claude 3 Haiku
- GPT-4
How this works
One link, either order
This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.