Skip to content

Google

gemini-2.5-flash benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place gemini-2.5-flash, 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

#33of 85

on the LLM leaderboard, with a consensus score of 54 across 2 leaderboards.

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

By leaderboard

Where each leaderboard places gemini-2.5-flash

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

#48of 79

Score 1410. Best run: gemini-2.5-flash.

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

Berkeley BFCL

#11of 37

Score 56.24%. Best run: Gemini-2.5-Flash (FC).

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

Price and context

$0.85

Vercel AI Gateway: $0.30 in, $2.50 out

Nearby

The models either side of gemini-2.5-flash

  1. #30deepseek-v3.258
  2. #31grok-4-070956
  3. #32GPT-5.6 Luna54
  4. #33gemini-2.5-flash54
  5. #34Claude Haiku 4.553
  6. #35Kimi K2.653
  7. #36qwen3-235b-a22b-instruct-250752

Questions about gemini-2.5-flash

How good is gemini-2.5-flash?
gemini-2.5-flash ranks #33 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 54 out of 100 across 2 leaderboards.
Is gemini-2.5-flash better than GPT-5.6 Luna?
Not on the consensus: GPT-5.6 Luna scores 54 to gemini-2.5-flash's 54. Compare them source by source below, since the leaderboards test different things.
Is gemini-2.5-flash better than Claude Haiku 4.5?
On the consensus, yes: 54 to 53.
How much does gemini-2.5-flash cost?
$0.30 per million input tokens and $2.50 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $0.85 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.