MMODELYST
Models/GPT-4 Turbo
MDL

GPT-4 Turbo

OpenAI

Verified against Artificial Analysis · Jul 13, 2026
Capability
46
percentile index
Price /M
$10 / $30
in / out
Context
128K
tokens
Avg score
41.5
5 benchmarks
AA Intelligence
7.9
index
Speed
38 tok/s
TTFT 1.3s
Released
Nov 6, 2023
About

GPT-4 Turbo is a proprietary model in the GPT family from OpenAI. Benchmarked on 5 evals, averaging 41.5.

Benchmark scores · 5
avg 41.5 — higher is better
MATH
73.7
MMLU-Pro
69.4
SciCode
31.9
LiveCodeBench
29.1
Humanity's Last Exam
3.3
Details
PublisherOpenAI
FamilyGPT
Parameters
License
WeightsClosed
ReleasedNov 6, 2023
Performance & price
Output speed38 tok/s
Latency (TTFT)1.3s
Price in / out$10 / $30 per 1M
Blended price$15 / 1M
Coding index21.5

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$30/M