Patchwire

OpenAI · Released Dec 10, 2025

GPT-5.2 Pro

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

ReasoningVision
  • Top 12%Chess Puzzles
  • Top 31%FrontierMath
  • Top 36%FrontierMath Tier 4
  • Top 43%ARC-AGI-1
Compare in showdown → OpenRouter ↗ All OpenAI models
Released
Dec 10 2025
Context window
400K 128K out
Input / 1M tokens
$21.00
Output / 1M tokens
$168.00

Where to run it

Providers

Only OpenAI serves GPT-5.2 Pro on OpenRouter right now.

ProviderInputOutputContextMax outputUptimevs. best
OpenAI $21.00 $168.00 400K128K100%24h Cheapest

Value

Price vs. performance

35 models score higher for the same price or lesson ARC-AGI-2, e.g. GPT-6 Astra.
1.3%32.5%63.8%95.0% $0.01$0.10$1.00$10.00$100.00 DeepSeek V4.1 Flash 1017 (DeepSeek) — 72.9% · $0.30/1M in Gemini 4 Argon (Google) — 91.3% · $2.00/1M in Claude Haiku 5.5 (Anthropic) — 61.3% · $0.10/1M in Claude Opus 5.5 (Anthropic) — 93.3% · $4.00/1M in Grok 4.7 (xAI) — 61.4% · $2.00/1M in DeepSeek V4.1 Flash (DeepSeek) — 72.9% · $0.056/1M in Gemini 3.8 Flash (Google) — 89.2% · $0.82/1M in Claude Fable 5.1 (Anthropic) — 90.0% · $10.00/1M in GLM 5.3 Flash (Z.ai) — 65.8% · $0.047/1M in Qwen3.8 27B (Qwen) — 42.4% · $0.04/1M in Gemini 3.7 Flash (Google) — 84.6% · $0.75/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 61.3% · $0.66/1M in Grok 4.6 (xAI) — 67.1% · $2.00/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 61.4% · $0.44/1M in Claude Opus 5 (Anthropic) — 90.4% · $5.00/1M in Gemini 3.6 Flash (Google) — 60.4% · $0.75/1M in Gemini 3.5 Flash Lite (Google) — 10.3% · $0.30/1M in Kimi K3 (Moonshot AI) — 60.4% · $0.24/1M in Grok 4.5 (xAI) — 52.6% · $2.00/1M in GLM 5.2 (Z.ai) — 22.8% · $0.62/1M in Claude Fable 5 (Anthropic) — 89.2% · $10.00/1M in Claude Opus 4.8 (Anthropic) — 72.1% · $5.00/1M in Gemini 3.5 Flash (Google) — 72.1% · $1.50/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 61.3% · $0.95/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 61.4% · $0.091/1M in Claude Opus 4.7 (Anthropic) — 75.8% · $5.00/1M in Grok 4.20 (xAI) — 65.1% · $1.25/1M in Gemini 3.1 Pro Preview (Google) — 77.1% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 60.4% · $3.00/1M in MiniMax M2.5 (MiniMax) — 4.9% · $0.27/1M in GLM 5 (Z.ai) — 4.9% · $0.60/1M in Claude Opus 4.6 (Anthropic) — 69.2% · $5.00/1M in Kimi K2.5 (Moonshot AI) — 11.8% · $0.50/1M in Gemini 3 Flash Preview (Google) — 33.6% · $0.50/1M in DeepSeek V3.2 (DeepSeek) — 4.0% · $0.28/1M in Claude Opus 4.5 (Anthropic) — 37.6% · $5.00/1M in Claude Haiku 4.5 (Anthropic) — 4.0% · $1.00/1M in Claude Sonnet 4.5 (Anthropic) — 13.6% · $3.00/1M in DeepSeek V3.2 Exp (DeepSeek) — 4.0% · $0.27/1M in Gemini 2.5 Pro (Google) — 4.9% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 4.9% · $1.25/1M in R1 0528 (DeepSeek) — 1.3% · $0.50/1M in GPT-6.1 Sol (OpenAI) — 94.2% · $2.00/1M in GPT-6 Luna (OpenAI) — 59.3% · $0.10/1M in GPT-6 Sol (OpenAI) — 89.6% · $2.00/1M in GPT-6 Astra (OpenAI) — 95.0% · $10.00/1M in GPT-5.6 Luna (OpenAI) — 59.5% · $0.20/1M in GPT-5.6 Terra (OpenAI) — 83.9% · $2.00/1M in GPT-5.6 Sol (OpenAI) — 92.5% · $4.00/1M in GPT-5.5 Pro (OpenAI) — 84.6% · $30.00/1M in GPT-5.5 (OpenAI) — 85.0% · $5.00/1M in GPT-5.4 Nano (OpenAI) — 5.7% · $0.20/1M in GPT-5.4 Mini (OpenAI) — 18.9% · $0.75/1M in GPT-5.4 Pro (OpenAI) — 83.3% · $30.00/1M in GPT-5.4 (OpenAI) — 74.0% · $2.50/1M in GPT-5.2 (OpenAI) — 52.9% · $1.75/1M in GPT-5.1 (OpenAI) — 17.6% · $1.25/1M in GPT-5 Pro (OpenAI) — 18.3% · $15.00/1M in GPT-5 (OpenAI) — 9.9% · $1.25/1M in GPT-5 Mini (OpenAI) — 4.4% · $0.25/1M in GPT-5 Nano (OpenAI) — 2.6% · $0.05/1M in o3 Pro (OpenAI) — 4.9% · $20.00/1M in GPT-5.2 Pro (OpenAI) — 54.2% · $21.00/1M in GPT-5.2 Pro

GPT-5.2 Pro Other OpenAI Other labs Value frontier · ARC-AGI-2 vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

6 benchmark scores

BenchmarkScoreRankLeader
ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles 54.2% #38of 63 GPT-6 Astra95.0%
ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples 90.5% #27of 63 Gemini 4 Argon98.5%
SimpleBenchReasoning & knowledge · Common-sense trick questions about space, time and people 57.4% #26of 43 Claude Fable 581.9%
Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles 60.0% #8of 70 GPT-6 Astra76.0%
FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) 74.0% #22of 72 GPT-6.1 Sol93.7%
FrontierMath Tier 4Maths · Exceptionally hard research-level problems 46.0% #22of 62 GPT-6.1 Sol100.0%

Specs

Details

Model ID
openai/gpt-5.2-pro
Developer
OpenAI
Release date
Dec 10, 2025 ·
Context window
400,000 tokens
Max output
128,000 tokens
API price
$21.00 / $168.00 per 1M input / output tokens
Providers
1
Input types
image, text, file
Reasoning
Yes
Tool calling
Yes
Open weights
No
Free tier
No

Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.