MDL
GPT-3.5 Turbo
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
55
percentile index
Price /M
$0.5 / $1.5
in / out
Context
16.4K
tokens
Avg score
40.0
3 benchmarks
AA Intelligence
3.6
index
Speed
147 tok/s
TTFT 0.8s
Released
Nov 30, 2022
About
GPT-3.5 Turbo is a proprietary model in the GPT family from OpenAI. Benchmarked on 3 evals, averaging 40.0.
Benchmark scores · 3
avg 40.0 — higher is betterThe research behind this model
all papers mentioning it →WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct27 cites · Aug 18, 20232 OLMo 2 Furious2 cites · Dec 31, 2024
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed147 tok/s
Latency (TTFT)0.8s
Price in / out$0.5 / $1.5 per 1M
Blended price$0.75 / 1M
Coding index10.7
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$1.5/M