GPT-5.2

OpenAIProprietaryReleased Dec 11, 2025

GPT-5.2 is not on the arena.ai Agents leaderboard, so it has no rank on our default leaderboard; the other data below is for reference. GPT-5.2 ranks #101 on the LMArena Text leaderboard (style control) with an Arena score of 1437.4 (±3.6, 49,622 votes). API price: $1.75 input / $14.00 output per 1M tokens. Context: 400K. Nearest rivals: Grok 4.7 (1441.8) above and MiniMax M3 (1435.9) below.

Quick answer

Agents leaderboard
No result yet
Text (LMArena)
#101 · 1437.4
API price (in / out)
$1.75 / $14.00 per 1M tokens
Closest rival
Grok 4.7 · 1441.8
Data updated
Nov 7, 2026 · synced daily

Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter

Key metrics

Agent Net Improvement–arena.ai Agents
Arena score1437.4±3.6LMArena #101 · 49,622 votes
Intelligence–Variant: xhigh
Coding–Artificial Analysis
Writing (creative)1376.0±7.3LMArena creative writing #136 / 417
List price in / out$1.75 / $14.00USD per 1M tokens
Lowest route$1.75 / $14.00Cheapest OpenRouter route
Context400Ktokens
Output speed–AA measured median
TTFT / first answer–AA measured median

Rank history

LMArena rank, last 23 days
#100#102#104Oct 16Nov 7

#102 on Oct 16, #101 now; best #101 in this period.

Models ranked nearby

Sorted by Arena score
#ModelArenaIntel.Output $tok/s
53Kimi K2.51449.7–$3.00–
54Gemini 2.5 Pro1445.4–$10.00–
55Grok 4.71441.835.5$6.0058
56GPT-5.2This page1437.4–$14.00–
57MiniMax M31435.918.9$1.20106
58DeepSeek V4 Flash1435.7–$0.28–
59MiMo V2.51433.8–$0.27–

More from OpenAI

#ModelArenaIntel.Output $tok/s
19GPT-5.6 Sol1485.4–$20.00–
21GPT-6.1 Sol1482.854.6$10.0061
25GPT-5.51481.5–$30.00–
28GPT-5.2 Chat1475.6–$14.00–
29GPT-5.41475.3–$15.00–
30GPT-6 Astra1475.156.9$50.0051

Pricing

  • Official API list price: $1.75 input and $14.00 output per 1M tokens (USD).
  • At a typical 3:1 input-to-output ratio, the blended cost is about $4.81 per 1M tokens.
  • Among 68 models with an output price, it is the #49 cheapest.
  • The cheapest OpenRouter route charges $1.75 input / $14.00 output.

Sources & methodology

GPT-5.2 is not on the arena.ai Agents leaderboard, so it has no rank on our default leaderboard; the other data below is for reference.

  • arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
  • LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
  • Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
  • OpenRouter — Route prices, context length and listing date.

Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).

Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.

FAQ

What rank is GPT-5.2 right now?

GPT-5.2 is #56 on our leaderboard of 64 scored models (Arena score 1437.4); its raw LMArena rank is #101.

What does GPT-5.2 cost via API?

Input $1.75 / output $14.00 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $4.81 per 1M tokens.

How close is GPT-5.2 to the models ranked next to it?

It is 4.4 points behind Grok 4.7 (1441.8) and 1.5 points ahead of MiniMax M3 (1435.9); gaps smaller than the confidence interval (±3.6) are not significant.

Is GPT-5.2 open source? Can it be self-hosted?

GPT-5.2 is a closed model, available only via official APIs or hosted services.

What is the context length of GPT-5.2?

400K (400,000 tokens, as listed on OpenRouter).

GPT-5.2 vs Grok 4.7: which is better?

On the LMArena Text leaderboard GPT-5.2 scores 1437.4 and Grok 4.7 scores 1441.8 (a 4.4-point gap, within the confidence interval, so not significant). On price, GPT-5.2 costs $14.00 and Grok 4.7 $6.00 per 1M output tokens.

Is there a cheaper model close to GPT-5.2?

Yes: Kimi K2.5 scores 1449.7 on the Text leaderboard (GPT-5.2: 1437.4) and costs $3.00 per 1M output tokens, about 79% less than GPT-5.2 ($14.00).

Where does the GPT-5.2 data come from and how often is it updated?

Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 7, 2026.

Related leaderboards