Google · proprietary

Gemini 2.5 Flash

Gemini 2.5 Flash by Google appears in 2 sources with Reasoning at 28.49. Best read for Coding, High intelligence, LLM.

CreatorGoogle

Release date2025-05-20

Knowledge cutoffNot published

Context1M tokens

Input price$0.3/M tokens

Output price$2.5/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank55ranking · source_rank

Reasoning28.49reasoning · index_reasoning

Math22.99math · index_math

Coding11.89coding · index_code

Vision16.83multimodal · index_vision

Long context18.66long_context · index_long_context

Healthcare33.01domain · index_healthcare

GPQA82.8 %reasoning · gpqa_score

AIME 202572 %math · aime_2025_score

SWE-bench Verified60.4 %coding · swe_bench_verified_score

Code Arena909.5 %coding · coding_arena_score

Humanity Last Exam11 %reasoning · hle_score

MMMU79.7 %multimodal · mmmu_score

SimpleQA26.9 %knowledge · simpleqa_score

Context1,048,576 tokenscontext · context

Speed72.53 c/sperformance · throughput

Latency9,090.25 msperformance · latency

Input price0.3 $/Mpricing · input_price

Output price2.5 $/Mpricing · output_price

Arena Rating1,417.95metric

Arena Rank80metric

Vote Count116,697metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Gemini 2.5 Flash verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.