BenchLeader

Gemini 2.5 Pro Preview 0325

Quality#47 of 366
59.7Index
Top quarter
+9.8 on the median

As of 22 Nov 2026, Gemini 2.5 Pro Preview 0325 by Google scores 59.7 on the BenchLeader Index (top 100 of 650 ranked configurations), with its best results in long context (73) and weakest in reasoning (52). Released 25 Mar 2025.

Key facts (as of 22 Nov 2026)

  • Gemini 2.5 Pro Preview 0325 was released on 25 Mar 2025 (Google).

In detail. Gemini 2.5 Pro Preview 0325 is a Google proprietary reasoning model, released 25 Mar 2025. Its best configuration ranks #100 of 650 on the BenchLeader Index at 59.7 ±3.4, in the upper half. The ± is the point: 224 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 (73) and lowest in reasoning (52). Last measured 13 Oct 2026.

Blended price
–
Output speed
–
First answer
–
Context
1M
via Artificial Analysis
Cost per task
–
Tokens per task
–
Released
25 Mar 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index60
  2. Reasoning52
  3. Coding61
  4. Maths59
  5. Knowledge56
  6. Instruction following58
  7. Multimodal71
  8. Long context73

Embed this rank

More badge styles
[![Gemini 2.5 Pro Preview 0325 on BenchLeader: #47 overall](https://www.benchleader.com/badge/gemini-2-5-pro-0325.svg?style=compact)](https://www.benchleader.com/models/gemini-2-5-pro-0325)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

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 2 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 2.5 Pro Preview 05066 May 202556.9#175
Gemini 2.5 Pro Preview 0325this page25 Mar 202559.7#100

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.

Reasoning

Benchmarknot statedSourceTrend
GPQA Diamond83.8%#115Epoch AI Benchmarking Hub
Humanity's Last Exam18.2%#25Scale AI / CAIS
SimpleBench51.6%#67SimpleBench
GPQA Diamond (AA)not in index83.6%#160Artificial Analysis
Humanity's Last Exam (AA)not in index18.0%#254Artificial Analysis
GPQA Diamond (Vals)not in index80.8%#66Vals AI
GPQA Diamond (HELM)not in index74.9%#5HELM Capabilities
HLE Text-Only (Scale)not in indexpossible contamination18.4%#23Scale AI SEAL
ForecastBenchnot in index64.0%#30ForecastBench

Coding

Agents & tools

Benchmarknot statedSourceTrend
BALROGnot in index43.3%#10BALROG

Maths

Benchmarknot statedSourceTrend
MATH Level 595.6%#13Epoch AI Benchmarking Hub
AIME (Vals)85.8%#35Vals AI
Omni-MATH (HELM)41.6%#28HELM Capabilities
MATH 500not in index95.2%#5Vals AI

Knowledge

Benchmarknot statedSourceTrend
MMLU-Pro84.1%#66Vals AI
LegalBench84.3%#35Vals AI
CorpFin59.8%#72Vals AI
TaxEval72.9%#56Vals AI
MedQA93.1%#25Vals AI
MMLU-Pro (HELM)not in index86.3%#4HELM Capabilities

Instruction following

Benchmarknot statedSourceTrend
IFEval (HELM)84.0%#25HELM Capabilities
WildBench (HELM)85.7%#6HELM Capabilities

Human preference

Benchmarknot statedSourceTrend
EQ-Bench Creative Writing v3not in index1396#78EQ-Bench
EQ-Bench Longform Writingnot in index58.8#66EQ-Bench
Lech Mazur Creative Writingnot in index80.5%#17Lech Mazur

Multimodal

Benchmarknot statedSourceTrend
VISTA54.6%#1Scale AI SEAL
MMMU-Pro (Vals)not in index81.3%#40Vals AI
MortgageTaxnot in index67.2%#28Vals AI
GeoBenchnot in index84.0%#7GeoBench
VPCTnot in index48.0%#11Epoch AI Benchmarking Hub

Long context

Benchmarknot statedSourceTrend
Fiction.LiveBench 120k90.6%#4Fiction.live

Composite

Safety & honesty

Benchmarknot statedSourceTrend
FORTRESSnot in index54.9%#81Scale AI SEAL
MASKnot in index55.9%#44Scale AI SEAL

Where it wins

Benchmarks where this configuration ranks in the top five of every configuration measured.

More from Google

New this month

Compare Gemini 2.5 Pro Preview 0325 with…

See also

Embed or cite

Show where Gemini 2.5 Pro Preview 0325 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.

[![Gemini 2.5 Pro Preview 0325 on BenchLeader: #47 overall](https://www.benchleader.com/badge/gemini-2-5-pro-0325.svg)](https://www.benchleader.com/models/gemini-2-5-pro-0325)

Cite this

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

BenchLeader. (2026, November 22). Gemini 2.5 Pro Preview 0325 on the BenchLeader Index (method v1.5) [Data set]. Retrieved November 22, 2026, from https://www.benchleader.com/models/gemini-2-5-pro-0325

BibTeX:

@misc{benchleader_gemini_2_5_pro_0325_20261122,
  author       = {{BenchLeader}},
  title        = {{Gemini 2.5 Pro Preview 0325 on the BenchLeader Index (method v1.5)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/gemini-2-5-pro-0325}},
  note         = {Data as of 2026-11-22}
}

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

Questions people ask

What are Gemini 2.5 Pro Preview 0325's benchmark scores?
As of 22 Nov 2026, Gemini 2.5 Pro Preview 0325 scores 59.7 ±3.4 on the BenchLeader Index, top 100, strongest in long context (73) and weakest in reasoning (52). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Gemini 2.5 Pro Preview 0325 rank?
Gemini 2.5 Pro Preview 0325 is #100 of 650 ranked configurations on 22 Nov 2026 (top 100). 224 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 70.2.
Is Gemini 2.5 Pro Preview 0325 better than GPT-5.6 Sol?
As of 22 Nov 2026, GPT-5.6 Sol (max) is the better pick for most workloads: it leads on quality (65.1 vs 59.7 on the BenchLeader Index). The head-to-head page has the benchmark-by-benchmark detail.
When was Gemini 2.5 Pro Preview 0325 released?
Google released Gemini 2.5 Pro Preview 0325 on 25 Mar 2025.

Data as of 22 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Gemini 2.5 Pro Preview 0325: benchmarks, pricing, speed and rank”, data as of 22 Nov 2026, https://www.benchleader.com/models/gemini-2-5-pro-0325.