Side-by-side comparison · models
GPT-4 vs GPT-4 Turbo
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
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.
Models
GPT-4 Turbo
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
Checked facts
Line by line
| Measure | GPT-4 | GPT-4 Turbo |
|---|---|---|
| Input price | $30.00 per million tokens | $5.00 per million tokens |
| Output price | $60.00 per million tokens | $15.00 per million tokens |
| Latest version | openai/gpt-4 | openai/gpt-4-turbo |
| Time to first token (ms) | Not checked yet | 1,770 |
| Output speed (tokens a second) | Not checked yet | 149.4 |
| Tokens served on OpenRouter in a day | 4.6M (for 10 Nov 2026) | 2.1M (for 23 Oct 2026) |
| Tool calls on OpenRouter in a day | 195 (for 10 Nov 2026) | 34 (for 23 Oct 2026) |
| Artificial Analysis Intelligence Index | 6.7 | 7 |
| Artificial Analysis Coding Index | 13.1 | 21.5 |
| LMArena text rating (Elo) | 1,206 | 1,272 |
| LMArena vision rating (Elo) | Not checked yet | 1,090 |
| Dtbench | Not checked yet | 61.6% (for 6 Nov 2023) |
| Lmca | Not checked yet | 9.8% (for 6 Nov 2023) |
| Mmlu | Not checked yet | 79.6% (for 6 Nov 2023) |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.