BenchLeader

Gemini 2.5 Pro Preview 0506

Quality#86 of 366
56.9Index
Top quarter
+7.0 on the median
Price#203 of 273
$3.44per 1M tokens
Dearer than most
3.7× the median
Value#204 of 273
16.6points per $
Below the median
0.3× the median

Better value: DeepSeek V4 Flash 0420 scores 58.3 for $0.117/M, 29× cheaper.

34 cheaper ranked models score higher: Gemini 4 Hydrogen (64.8, $3.00), GPT-6.1 Terra (63.1, $2.00), Gemini 3.5 Flash (62.4, $3.38) and 31 more.

As of 22 Nov 2026, Gemini 2.5 Pro Preview 0506 by Google scores 56.9 on the BenchLeader Index (650 ranked configurations), with its best results in maths (69) and weakest in reasoning (48). API pricing: $1.25 per 1M input tokens and $10.00 per 1M output tokens ($3.44 blended at 3:1), list price on 22 Nov 2026. Released 6 May 2025.

Key facts (as of 22 Nov 2026)

  • Gemini 2.5 Pro Preview 0506 API pricing: $1.25 per 1M input tokens and $10.00 per 1M output tokens ($3.44 blended at 3:1) (list price, 22 Nov 2026).
  • Gemini 2.5 Pro Preview 0506 was released on 6 May 2025 (Google).

In detail. Gemini 2.5 Pro Preview 0506 is a Google proprietary reasoning model, released 6 May 2025. Its best configuration ranks #175 of 650 on the BenchLeader Index at 56.9 ±6.6, in the upper half. The ± is the point: 337 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 maths (69) and lowest in reasoning (48). At $3.44 per million tokens blended it is pricier than most ranked models. Last measured 26 Jul 2025.stale: no new result in six months

Blended price
$3.44/M
$1.25 in · $10.00 out
via Artificial Analysis
Output speed
–
First answer
–
Context
1M
via Artificial Analysis
Cost per task
–
Tokens per task
–
Released
6 May 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index57
  2. Reasoning48
  3. Coding58
  4. Maths69
  5. Multimodal65
  6. Long context60

Embed this rank

More badge styles
[![Gemini 2.5 Pro Preview 0506 on BenchLeader: #86 overall](https://www.benchleader.com/badge/gemini-2-5-pro-0506.svg?style=compact)](https://www.benchleader.com/models/gemini-2-5-pro-0506)

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 0506this page6 May 202556.9#175
Gemini 2.5 Pro Preview 032525 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 Diamond66.7%#197Epoch AI Benchmarking Hub
Humanity's Last Exam17.8%#27Scale AI / CAIS
GPQA Diamond (AA)not in index82.2%#178Artificial Analysis
Humanity's Last Exam (AA)not in index19.9%#235Artificial Analysis
HLE Text-Only (Scale)not in indexpossible contamination18.4%#23Scale AI SEAL

Agents & tools

Benchmarknot statedSourceTrend
TheAgentCompanynot in index30.3%#5TheAgentCompany

Maths

Benchmarknot statedSourceTrend
MATH Level 595.9%#12Epoch AI Benchmarking Hub

Human preference

Benchmarknot statedSourceTrend
Lech Mazur Creative Writingnot in index80.9%#16Lech Mazur

Multimodal

Benchmarknot statedSourceTrend
VISTA50.8%#10Scale AI SEAL
GeoBenchnot in index86.0%#3GeoBench
VPCTnot in index40.5%#16Epoch AI Benchmarking Hub

Long context

Benchmarknot statedSourceTrend
Fiction.LiveBench 120k71.9%#9Fiction.live

Composite

Benchmarknot statedSourceTrend
Epoch Capabilities Indexnot in index140.6#121Epoch AI Benchmarking Hub
AA Intelligence Index v4.3.2not in index14.5#308Artificial Analysis
AA Progress Index v1not in index242.6#322Artificial Analysis

Safety & honesty

Benchmarknot statedSourceTrend
MASKnot in indexpossible contamination53.1%#47Scale AI SEAL

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.125 per 1M. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0035$0.0032–
Summarize a 30-page report12,000 / 600$0.021$0.011–
Code edit6,000 / 1,500$0.022$0.017–
Agentic coding session60,000 / 4,000$0.115$0.064–
Structured extraction2,000 / 200$0.0045$0.0028–

More from Google

New this month

See also

Embed or cite

Show where Gemini 2.5 Pro Preview 0506 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 0506 on BenchLeader: #86 overall](https://www.benchleader.com/badge/gemini-2-5-pro-0506.svg)](https://www.benchleader.com/models/gemini-2-5-pro-0506)

Cite this

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

BenchLeader. (2026, November 22). Gemini 2.5 Pro Preview 0506 on the BenchLeader Index (method v1.5) [Data set]. Retrieved November 22, 2026, from https://www.benchleader.com/models/gemini-2-5-pro-0506

BibTeX:

@misc{benchleader_gemini_2_5_pro_0506_20261122,
  author       = {{BenchLeader}},
  title        = {{Gemini 2.5 Pro Preview 0506 on the BenchLeader Index (method v1.5)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/gemini-2-5-pro-0506}},
  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 0506's benchmark scores?
As of 22 Nov 2026, Gemini 2.5 Pro Preview 0506 scores 56.9 ±6.6 on the BenchLeader Index, strongest in maths (69) and weakest in reasoning (48). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Gemini 2.5 Pro Preview 0506 rank?
Gemini 2.5 Pro Preview 0506 is #175 of 650 ranked configurations on 22 Nov 2026. 337 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.
How much does Gemini 2.5 Pro Preview 0506 cost per 1M tokens?
As of 22 Nov 2026, Gemini 2.5 Pro Preview 0506 costs $1.25 per 1M input tokens and $10.00 per 1M output tokens, $3.44 blended (three input tokens per output token).
When was Gemini 2.5 Pro Preview 0506 released?
Google released Gemini 2.5 Pro Preview 0506 on 6 May 2025.

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

Cite as: BenchLeader, “Gemini 2.5 Pro Preview 0506: benchmarks, pricing, speed and rank”, data as of 22 Nov 2026, https://www.benchleader.com/models/gemini-2-5-pro-0506.