OpenAIGPT-4Arena #145Apr 9, 2024
OpenAI: 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.
Context Window
128K
tokens
Max Output
4K
tokens
Released
Apr 9, 2024
Arena Rank
#145
of 305 models
Output Speed
92
tokens/sec
Time to First Token
420ms
TTFT
Capabilities
👁Vision
🧠Reasoning
🔧Tool Calling
⚡Prompt Caching
🖥Computer Use
🎨Image Generation
Supported Parameters
Frequency Penalty
Reduce repetition
Logit Bias
Adjust token weights
Log Probs
Token probabilities
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
structured_outputs
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
top_logprobs
Top P
Nucleus sampling
Pricing Comparison
| Router | Input / 1M | Output / 1M | Cached Input / 1M |
|---|---|---|---|
| OpenRouter | $10.00 | $30.00 | — |
| Vercel AI | $10.00 | $30.00 | — |
| Martian | $30.00 | $60.00 | — |
Benchmarks
Artificial Analysis
Intelligence IndexArtificial Analysis
54.4/100Coding IndexArtificial Analysis
42.8/100Math IndexArtificial Analysis
60.8/100MMLU-PROArtificial Analysis
0.724/1GPQA DiamondArtificial Analysis
0.538/1MATH-500Artificial Analysis
0.763/1AIME 2024Artificial Analysis
0.097/1Humanity's Last ExamArtificial Analysis
0.013/1LiveCodeBenchArtificial Analysis
0.395/1SciCodeArtificial Analysis
0.158/1Model IDs
OpenRouter
openai/gpt-4-turboTags
visiontool-calling