DataLearner logo

GPT-5.2vsGPT-5.1

Across 14 shared benchmarks, GPT-5.2 leads overall: GPT-5.2 wins 12, GPT-5.1 wins 1, with 1 ties and an average score difference of +6.49.

OpenAI
GPT-5.2

OpenAI · 2025-12-11 · Chat model

OpenAI
GPT-5.1

OpenAI · 2025-11-12 · Reasoning model

GPT-5.212 wins(86%)Ties1(7%)1 winGPT-5.1

Benchmark scores

Grouped by capability, sorted by largest gap within each. 14 shared benchmarks.

Math and Reasoning

GPT-5.2 3/3
BenchmarkGPT-5.2GPT-5.1Diff
AIME202551153 / 215Normal (No Tools)38170 / 215Normal (No Tools)+13
MathArena Apex13.5413 / 17Thinking High (With Tools)1.0414 / 17Thinking High (With Tools)+12.50
FrontierMath - Tier 418.8016 / 80Thinking High (No Tools)12.5029 / 80Thinking High (No Tools)+6.30

Agent Level Benchmark

GPT-5.2 1/2
BenchmarkGPT-5.2GPT-5.1Diff
Terminal Bench Hard31.80100 / 244Normal (With Tools)22.70143 / 244Normal (With Tools)+9.10
τ²-Bench - Telecom46.50178 / 264Normal (With Tools)46.50178 / 264Normal (With Tools)

Coding and Software Engineer

GPT-5.2 2/2
BenchmarkGPT-5.2GPT-5.1Diff
LiveCodeBench66.90103 / 250Normal (No Tools)49.40167 / 250Normal (No Tools)+17.50
GSO27.407 / 21Thinking High (With Tools)13.7013 / 21Thinking High (With Tools)+13.70

General Knowledge

GPT-5.2 2/2
BenchmarkGPT-5.2GPT-5.1Diff
LiveBench48.9196 / 117Normal (No Tools)42.65108 / 117Normal (No Tools)+6.26
HLE8419 / 563Normal (No Tools) · Text only5.30471 / 563Normal (No Tools) · Text only+2.70

Commonsense Reasoning

GPT-5.1 1/1
BenchmarkGPT-5.2GPT-5.1Diff
SimpleBench45.8058 / 93Thinking High (No Tools)53.2045 / 93Thinking High (No Tools)-7.40

General Evaluation

GPT-5.2 1/1
BenchmarkGPT-5.2GPT-5.1Diff
GPQA Diamond73.23298 / 462Normal (No Tools)64.30361 / 462Normal (No Tools)+8.93

Instruction Following

GPT-5.2 1/1
BenchmarkGPT-5.2GPT-5.1Diff
IF Bench47.40168 / 282Normal (No Tools)43.20192 / 282Normal (No Tools)+4.20

Long Context

GPT-5.2 1/1
BenchmarkGPT-5.2GPT-5.1Diff
AA-LCR45.70144 / 170Normal (No Tools)45147 / 170Normal (No Tools)+0.70

Multimodal Understanding

GPT-5.2 1/1
BenchmarkGPT-5.2GPT-5.1Diff
MMMU-Pro65.80148 / 227Normal (No Tools)62.40163 / 227Normal (No Tools)+3.40

Specs

FieldGPT-5.2GPT-5.1
PublisherOpenAIOpenAI
Release date2025-12-112025-11-12
Model typeChat modelReasoning model
ArchitectureDenseDense
ParametersNot availableNot available
Context length400K400K
Max outputNot available128K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGPT-5.2GPT-5.1
Text input$1.75 / 1M tokens$1.25 / 1M tokens
Text output$14 / 1M tokens$10 / 1M tokens
Cache read$0.175 / 1M tokens$0.125 / 1M tokens
Cache write$1.75 / 1M tokens$0 / 1M tokens

Summary

  • GPT-5.2leads in:Math and Reasoning (3/3), Agent Level Benchmark (1/2), Coding and Software Engineer (2/2), General Knowledge (2/2), General Evaluation (1/1), Instruction Following (1/1), Long Context (1/1), Multimodal Understanding (1/1)
  • GPT-5.1leads in:Commonsense Reasoning (1/1)

On average across the 14 shared benchmarks, GPT-5.2 scores 6.49 higher.

Largest single-benchmark gap: LiveCodeBench — GPT-5.2 66.90 vs GPT-5.1 49.40 (+17.50).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.