Skip to content
Get my AI grade

OpenAI

GPT 5.2 (2025-12-11) High benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GPT 5.2 (2025-12-11) High, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Oct 1, 2026Full leaderboardSources and method

Read Oct 1, 2026

#27of 85

on the LLM leaderboard, with a consensus score of 59 across 3 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places GPT 5.2 (2025-12-11) High

Artificial Analysis

Not measured by Artificial Analysis.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

#14of 34

Score 74.6. Best run: GPT 5.2 (2025-12-11) High.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

#34of 79

Score 1437. Best run: gpt-5.2-high.

Blind head-to-head human votes, style controlled.

Berkeley BFCL

#12of 37

Score 55.87%. Best run: GPT-5.2-2025-12-11 (FC).

Function calling and tool use, single turn to multi turn and web search.

Price and context

$4.81

Vercel AI Gateway: $1.75 in, $14 out LiveBench cost per solved task $0.234.

Nearby

The models either side of GPT 5.2 (2025-12-11) High

  1. #24o3-2025-04-1662
  2. #25Qwen3.7 Max61
  3. #26Claude Sonnet 4.660
  4. #27GPT 5.2 (2025-12-11) High59
  5. #28Qwen3.7 Plus59
  6. #29DeepSeek V4 Pro 042358
  7. #30deepseek-v3.258

Questions about GPT 5.2 (2025-12-11) High

How good is GPT 5.2 (2025-12-11) High?
GPT 5.2 (2025-12-11) High ranks #27 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 59 out of 100 across 3 leaderboards.
Is GPT 5.2 (2025-12-11) High better than Claude Sonnet 4.6?
Not on the consensus: Claude Sonnet 4.6 scores 60 to GPT 5.2 (2025-12-11) High's 59. Compare them source by source below, since the leaderboards test different things.
Is GPT 5.2 (2025-12-11) High better than Qwen3.7 Plus?
On the consensus, yes: 59 to 59.
How much does GPT 5.2 (2025-12-11) High cost?
$1.75 per million input tokens and $14 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $4.81 per million.

These models recommend brands. See if they name yours.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.