BenchLeader

Gemini 2.5 Flash 09 2025

Reasoning effort
Quality#131 of 333
52.9Index
Above the median
+2.9 on the median

As of 8 Nov 2026, Gemini 2.5 Flash 09 2025 by Google scores 52.9 on the BenchLeader Index (593 ranked configurations), with its best results in long context (60) and weakest in agents & tools (48). Released 25 Sep 2025.

Key facts (as of 8 Nov 2026)

  • Gemini 2.5 Flash 09 2025 was released on 25 Sep 2025 (Google).

In detail. Gemini 2.5 Flash 09 2025 is a Google proprietary reasoning model, released 25 Sep 2025. Its best configuration (thinking reasoning effort) ranks #263 of 593 on the BenchLeader Index at 52.9 ±2.2, in the upper half. The ± is the point: 262 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (60) and lowest in agents & tools (48). It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 13 Oct 2026.

Blended price
–
Output speed
–
First answer
–
Context
1M
via Artificial Analysis
Full answer
–
Cost per task
–
Tokens per task
–
Released
25 Sep 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index53
  2. Coding55
  3. Agents & tools48
  4. Maths48
  5. Knowledge55
  6. Instruction following53
  7. Multimodal55
  8. Long context60

Get an email when Google ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

Versions

Google has shipped 12 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Gemini 3.8 Flashhigh2 Sep 202662.0#57
Gemini 3.7 Flashhigh13 Aug 202662.2#54
Gemini 3.6 Flashhigh21 Jul 202661.3#64
Gemini 3.5 Flashhigh19 May 202662.5#48
Gemini 3 Flashthinking17 Dec 202558.9#112
Gemini 2.5 Flash 09 2025thinkingthis page25 Sep 202552.9#263
Gemini 2.5 Flash17 Apr 202552.7#265
Gemini 2.0 Flash5 Feb 202543.4#470
Gemini 1.5 Flash 00224 Sep 202438.1#550
Gemini 1.5 Flash 00123 May 2024––
Gemini 1.5 Flash14 May 202445.1#449
Gemini Flash 2.0–––

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.

EffortIndexRankSpeedFirst answerChat reply costCategories
no reasoning–––––Agents & tools 46 · Instruction following 46 · Long context 54 · Multimodal 53
thinkingbest52.9#263–––Agents & tools 48 · Coding 55 · Instruction following 53 · Knowledge 55 · Long context 60 · Maths 48 · Multimodal 55
not stated46.8#411–––Agents & tools 30 · Coding 51 · Knowledge 55 · Maths 48

How its index has moved

10 Sep 2026 to 8 Nov 2026
445055
  • thinking
  • not stated

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Metadata

BenchmarkthinkingSource
AA Openness Indexnot in index5.6#55Artificial Analysis

Reasoning

Benchmarkno reasoningthinkingnot statedSource
GPQA Diamond (AA)not in index76.6%#23579.3%#202–Artificial Analysis
Humanity's Last Exam (AA)not in index8.7%#35713.8%#276–Artificial Analysis
GPQA Diamond (Vals)not in index–76.5%#7681.6%#63Vals AI
CritPtnot in index0.0%#3290.3%#283–Artificial Analysis

Coding

Benchmarkno reasoningthinkingnot statedSource
WeirdMLeffort not stated––41.9%#94WeirdML
LiveCodeBench–76.2%#7875.1%#79Vals AI
Design Arena Websitenot in indexeffort not stated––1113#136Design Arena
LiveCodeBench (AA)not in index62.5%#10371.3%#59–Artificial Analysis

Agents & tools

Benchmarkno reasoningthinkingnot statedSource
Terminal-Bencheffort not stated––17.1%#76Terminal-Bench
Terminal-Bench Hard14.4%#20116.7%#188–Artificial Analysis
τ²-Bench Telecom (AA)not in index28.4%#27245.6%#213–Artificial Analysis
Terminal-Bench 2.0 (Vals)not in index–21.4%#57–Vals AI
TheAgentCompanynot in indexeffort not stated––41.1%#2TheAgentCompany

Maths

Benchmarkthinkingnot statedSource
AIME (Vals)51.5%#6049.8%#61Vals AI
MGSM89.8%#4289.8%#41Vals AI

Knowledge

Benchmarkthinkingnot statedSource
MMLU-Pro83.7%#7083.7%#69Vals AI
LegalBench82.6%#6782.5%#70Vals AI
CorpFin59.8%#7359.0%#79Vals AI
TaxEval72.4%#6272.7%#58Vals AI
MedQA91.2%#4091.4%#37Vals AI
MedCodenot in index40.3%#6640.5%#64Vals AI
MedScribenot in index78.5%#6578.0%#68Vals AI
Global-MMLU-Lite (AA)not in index88.8%#18–Artificial Analysis

Instruction following

Benchmarkno reasoningthinkingSource
IFBench43.5%#22552.3%#163Artificial Analysis

Multimodal

Benchmarkno reasoningthinkingnot statedSource
MMMU-Pro70.2%#15873.1%#137–Artificial Analysis
MMMU-Pro (Vals)not in index–80.8%#4379.5%#47Vals AI
MortgageTaxnot in index–61.9%#5762.6%#52Vals AI
VPCTnot in indexeffort not stated––46.2%#12Epoch AI Benchmarking Hub

Long context

Benchmarkno reasoningthinkingSource
AA-LCR v1.160.0%#29371.0%#215Artificial Analysis

Composite

Benchmarkno reasoningthinkingSource
AA Intelligence Index v4.3.2not in index12.4#34415.5#292Artificial Analysis
AA Progress Index v1not in index217.1#357235.3#301Artificial Analysis

More from Google

New this month

See also

Embed or cite

Show where Gemini 2.5 Flash 09 2025 ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.

[![Gemini 2.5 Flash 09 2025 on BenchLeader: #130 overall](https://www.benchleader.com/badge/gemini-2-5-flash-09-2025.svg)](https://www.benchleader.com/models/gemini-2-5-flash-09-2025)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 8). Gemini 2.5 Flash 09 2025 on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 8, 2026, from https://www.benchleader.com/models/gemini-2-5-flash-09-2025

BibTeX:

@misc{benchleader_gemini_2_5_flash_09_2025_20261108,
  author       = {{BenchLeader}},
  title        = {{Gemini 2.5 Flash 09 2025 on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/gemini-2-5-flash-09-2025}},
  note         = {Data as of 2026-11-08}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Gemini 2.5 Flash 09 2025's benchmark scores?
As of 8 Nov 2026, Gemini 2.5 Flash 09 2025 (thinking effort) scores 52.9 ±2.2 on the BenchLeader Index, strongest in long context (60) and weakest in agents & tools (48). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Gemini 2.5 Flash 09 2025 rank?
Gemini 2.5 Flash 09 2025 (thinking effort) is #263 of 593 ranked configurations on 8 Nov 2026. 262 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 69.4.
When was Gemini 2.5 Flash 09 2025 released?
Google released Gemini 2.5 Flash 09 2025 on 25 Sep 2025. BenchLeader has results for it at 3 reasoning-effort settings.

Data as of 8 Nov 2026. Compare these configurations.

Cite as: BenchLeader, “Gemini 2.5 Flash 09 2025: benchmarks, pricing, speed and rank”, data as of 8 Nov 2026, https://www.benchleader.com/models/gemini-2-5-flash-09-2025.