Skip to content

OpenAI

gpt-5-mini-high benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place gpt-5-mini-high, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Nov 15, 2026Full leaderboardSources and method

Read Nov 15, 2026

#35of 69

on the LLM leaderboard, with a consensus score of 51 across 2 leaderboards.

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

By leaderboard

Where each leaderboard places gpt-5-mini-high

Artificial Analysis

Not measured by Artificial Analysis.

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

LiveBench

Not measured by LiveBench.

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

LMArena

#44of 66

Score 1390. Best run: gpt-5-mini-high.

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

Berkeley BFCL

#12of 36

Score 55.46%. Best run: GPT-5-mini-2025-08-07 (FC).

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

Price and context

$0.69

Vercel AI Gateway: $0.25 in, $2.00 out

Nearby

The models either side of gpt-5-mini-high

  1. #32gpt-4.1-2025-04-1453
  2. #33GPT-5.6 Luna53
  3. #34qwen3-235b-a22b-instruct-250752
  4. #35gpt-5-mini-high51
  5. #36Inkling xHigh48
  6. #37o4-mini-2025-04-1648
  7. #38Kimi K2.6 Thinking48

Questions about gpt-5-mini-high

How good is gpt-5-mini-high?
gpt-5-mini-high ranks #35 of 69 models on the Rank.ai LLM leaderboard, with a consensus score of 51 out of 100 across 2 leaderboards.
Is gpt-5-mini-high better than qwen3-235b-a22b-instruct-2507?
Not on the consensus: qwen3-235b-a22b-instruct-2507 scores 52 to gpt-5-mini-high's 51. Compare them source by source below, since the leaderboards test different things.
Is gpt-5-mini-high better than Inkling xHigh?
On the consensus, yes: 51 to 48.
How much does gpt-5-mini-high cost?
$0.25 per million input tokens and $2.00 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $0.69 per million.

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.