Language modelActive

Gemini 2.5 Pro

Google

Released: June 17, 2025
Data date: September 8, 2026
Successor: Gemini 3 Pro Preview (Official documentation)

Speed: 131.3 tokens/s
Output throughput
Price: $1.25 · $10
Input · Output / 1M tokens
Input: Text, Image, Audio, Video
Output: Text

Gemini 2.5 Pro is distinguished by the stable GA Pro release and a 1,048,576-token context. Google now limits API access to users with prior 2.5 usage, while Gemini 3.1 Pro Preview shows the later Pro direction.

Audio, image, video, text, and PDF inputs fit into a 1,048,576-token context, with up to 65,536 output tokens. Its knowledge cutoff is January 2025.

Specifications and access

Specification	Value and source
Weights	ProprietarySource
Access	APISource
Context window	1,048,576 tokensSource
Knowledge cutoff	January 2025Source
Notes	1M context, parameter count not disclosedSource
API model ID	gemini-2.5-proSource
Source status	stableSource
Maximum output	65,536 tokensSource
Input	Text, Image, Video, Audio, pdfSource
Output	TextSource
Reasoning mode	low, medium, highSource
Tool calling	YesSource
Structured output	YesSource
Release	2025-06-17Source
Knowledge cutoff	2025-01Source
Capabilities	function calling, structured outputs, search grounding, Google Maps grounding, URL context, code execution, file searchSource
General availability	2025-06-17 (General availability (GA).)Source

Published benchmarks

Aider Polyglot

Overall

225 code-editing tasks from Exercism across C++, Go, Java, JavaScript, Python, and Rust. Aider, the edit format, reasoning budget, and two attempts are part of the result.

1.o3-pro84.9%

2.Gemini 2.5 Pro83.1%

3.o381.3%

4.DeepSeek-R171.4%

higher is betterAs of September 2, 2026Scale: 0% - 100%

Source: Aider

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: aider-polyglot-pass2-diff
Metric: percent correct after two attempts
Scale: 0-100
Participants: 4
Methodology and context: 225 Exercism tasks across six languages using Aider and a documented edit format.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Model snapshot: gemini-2.5-pro-preview-2025-06-05. Evaluator: Aider. Dataset type: public. Leaderboard date: 2025-06-06. Attempts: pass 2. Reasoning effort: 32k thinking tokens. Latency in seconds: 200.3. Cost per task in USD: 0.22169866666666666. Source ID: aider. Evidence capture ID: curated-aider-2026-09-02-b94f7308e188. Source payload hash: b94f7308e188d90f6864b22fd13d3d933378668e9fc981a7655173a4c3545a4e. Parser version: curated-v1. Imported at: 2026-09-29

Source: Aider

Knowledge

FACTS Benchmark Suite

3,513 public examples test factuality with documents, images, parametric knowledge, and web search. The suite score averages four different capabilities. The component scores matter more for decisions.

Sub-task	Gemini 2.5 Pro (This model)	GPT-5	Claude Opus 4.5	GPT-4.1
Document grounding	74.2% (best value in this row)	69.6%	62.1%	45.6%
Multimodal factuality	46.9% (best value in this row)	44.1%	39.2%	40.1%
FACTS overall score	62.1% (best value in this row)	61.8%	51.3%	50.5%
Parametric knowledge	63.2% (best value in this row)	55.8%	30.6%	51.5%
Factuality with search	63.9%	77.7% (best value in this row)	73.2%	64.6%

higher is betterAs of August 9, 2026Source: Google DeepMindbars scaled within each row, not across rows

Agent tasks

GAIA Reliability

Reliability evaluation on 165 GAIA tasks with repetitions and perturbations. Accuracy, reliability, consistency, predictability, robustness, and safety are separate metrics.

Sub-task	Gemini 2.5 Pro (This model)	Claude Opus 4.5	Claude Opus 4.7	Gemini 3.1 Pro Preview	Gemini 3.5 Flash	GPT-4o mini	Gemini 2.5 Flash	o1	GPT-5.5
Consistency	0.72	0.81 (best value in this row)	0.81 (best value in this row)	0.76	0.75	0.73	0.7	0.68	0.61
Predictability	0.71	0.84 (best value in this row)	0.73	0.78	0.8	0.58	0.64	0.68	0.8
Reliability	0.78	0.85 (best value in this row)	0.84	0.82	0.84	0.76	0.74	0.79	0.79
Robustness	0.91	0.91	0.99	0.94	0.96	0.97	0.87	1 (best value in this row)	0.95
Safety	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)	1 (best value in this row)

Unit: ratinghigher is betterAs of August 6, 2026Source: Princeton HALbars scaled within each row, not across rows

GAIA Reliability

Accuracy

Reliability evaluation on 165 GAIA tasks with repetitions and perturbations. Accuracy, reliability, consistency, predictability, robustness, and safety are separate metrics.

1.Gemini 3.5 Flash79.2%

2.Gemini 3.1 Pro Preview76.2%

3.Claude Opus 4.773.3%

4.Claude Opus 4.568.5%

5.GPT-5.562.8%

6.Gemini 2.5 Pro52.5%

7.Gemini 2.5 Flash46.7%

8.o134.4%

9.GPT-4o mini26.3%

higher is betterAs of August 6, 2026Scale: 0% - 100%

Source: Princeton HAL

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: hal-gaia-reliability-hal-reliability-overall
Metric: exact-match accuracy
Scale: 0-100
Participants: 9
Methodology and context: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-5c16f4ffaaa5. Source payload hash: 5c16f4ffaaa5ac8a5c682da01aa3fab9655de1625348891876a58ad2be1d678f. Parser version: curated-v1. Imported at: 2026-09-29

Source: Princeton HAL

Recorded measurement details

Aider Polyglot: Overall (Show measurement, test conditions, and source)

Source value: 83.1
Score: 83.1
Metric: percent correct after two attempts
Unit: %
Benchmark version: 225-case polyglot suite
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: aider-polyglot-pass2-diff
Source type: official-leaderboard
Evaluator: Aider
Status: active
Retrieved at: 2026-09-02
Methodology: 225 Exercism tasks across six languages using Aider and a documented edit format.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Model snapshot: gemini-2.5-pro-preview-2025-06-05. Evaluator: Aider. Dataset type: public. Leaderboard date: 2025-06-06. Attempts: pass 2. Reasoning effort: 32k thinking tokens. Latency in seconds: 200.3. Cost per task in USD: 0.22169866666666666. Source ID: aider. Evidence capture ID: curated-aider-2026-09-02-b94f7308e188. Source payload hash: b94f7308e188d90f6864b22fd13d3d933378668e9fc981a7655173a4c3545a4e. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 225 Exercism tasks across six languages using Aider and a documented edit format.

Source Aider

FACTS Benchmark Suite: Document grounding (Show measurement, test conditions, and source)

Source value: 74.2
Score: 74.2
Metric: accuracy
Unit: %
Benchmark version: FACTS Benchmark Suite v2
Category: knowledge
Task: grounding
Task label: Document grounding
Direction: Higher is better
Comparison cohort: facts-suite-v2:official:grounding
Confidence interval: 2
Source type: official-leaderboard
Evaluator: Google DeepMind
Status: active
Retrieved at: 2026-08-09
Methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Google DeepMind. Dataset type: public. Leaderboard date: 2025-12-11. Source ID: google-deepmind. Evidence capture ID: curated-google-deepmind-2026-08-09-8a8b1ae4abae. Source payload hash: 8a8b1ae4abae2b077a109193965fb09bce92092c2be809bfae78d4cfa219dc27. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.

Source Google DeepMind

FACTS Benchmark Suite: Multimodal factuality (Show measurement, test conditions, and source)

Source value: 46.9
Score: 46.9
Metric: accuracy
Unit: %
Benchmark version: FACTS Benchmark Suite v2
Category: knowledge
Task: multimodal
Task label: Multimodal factuality
Direction: Higher is better
Comparison cohort: facts-suite-v2:official:multimodal
Confidence interval: 3.6
Source type: official-leaderboard
Evaluator: Google DeepMind
Status: active
Retrieved at: 2026-08-09
Methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Google DeepMind. Dataset type: public. Leaderboard date: 2025-12-11. Source ID: google-deepmind. Evidence capture ID: curated-google-deepmind-2026-08-09-26c476d1beb7. Source payload hash: 26c476d1beb7b7772cf5b5a2e60452d78ae516f5f936f804b1cccfead5529b32. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.

Source Google DeepMind

FACTS Benchmark Suite: FACTS overall score (Show measurement, test conditions, and source)

Source value: 62.1
Score: 62.1
Metric: FACTS score
Unit: %
Benchmark version: FACTS Benchmark Suite v2
Category: knowledge
Task: overall
Task label: FACTS overall score
Direction: Higher is better
Comparison cohort: facts-suite-v2:official:overall
Source type: official-leaderboard
Evaluator: Google DeepMind
Status: active
Retrieved at: 2026-08-09
Methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Google DeepMind. Dataset type: public. Leaderboard date: 2025-12-11. Source ID: google-deepmind. Evidence capture ID: curated-google-deepmind-2026-08-09-f90e68e563fe. Source payload hash: f90e68e563fe354373076ca491cfa45c3d12df9ca257aa0eff56a191c63c53fa. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.

Source Google DeepMind

FACTS Benchmark Suite: Parametric knowledge (Show measurement, test conditions, and source)

Source value: 63.2
Score: 63.2
Metric: accuracy
Unit: %
Benchmark version: FACTS Benchmark Suite v2
Category: knowledge
Task: parametric
Task label: Parametric knowledge
Direction: Higher is better
Comparison cohort: facts-suite-v2:official:parametric
Confidence interval: 2
Source type: official-leaderboard
Evaluator: Google DeepMind
Status: active
Retrieved at: 2026-08-09
Methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Google DeepMind. Dataset type: public. Leaderboard date: 2025-12-11. Source ID: google-deepmind. Evidence capture ID: curated-google-deepmind-2026-08-09-68c34aa514b7. Source payload hash: 68c34aa514b740c6f80ada1a284136c938a1f97cd1e65c0f87138497fc92708c. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.

Source Google DeepMind

FACTS Benchmark Suite: Factuality with search (Show measurement, test conditions, and source)

Source value: 63.9
Score: 63.9
Metric: accuracy
Unit: %
Benchmark version: FACTS Benchmark Suite v2
Category: knowledge
Task: search
Task label: Factuality with search
Direction: Higher is better
Comparison cohort: facts-suite-v2:official:search
Confidence interval: 2
Source type: official-leaderboard
Evaluator: Google DeepMind
Status: active
Retrieved at: 2026-08-09
Methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Google DeepMind. Dataset type: public. Leaderboard date: 2025-12-11. Source ID: google-deepmind. Evidence capture ID: curated-google-deepmind-2026-08-09-36ddfd1bf586. Source payload hash: 36ddfd1bf586c681280b54cf509f9fbb4f8f41eeebb44d9a562d34aed96401d9. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: Public and private splits. Document, image, parametric knowledge, and standardized web search remain separate.

Source Google DeepMind

GAIA Reliability: Consistency (Show measurement, test conditions, and source)

Source value: 0.72
Score: 0.72
Metric: aggregate consistency
Unit: rating
Benchmark version: final leak-cleaned public validation set
Category: agentic
Task: consistency
Task label: Consistency
Direction: Higher is better
Comparison cohort: hal-gaia-reliability-hal-reliability-consistency
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-c31d0b9d9ce4. Source payload hash: c31d0b9d9ce4ae3176dd4e9d861282248ef948babbb34bde532eb1ccbbc96780. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.

Source Princeton HAL

GAIA Reliability: Predictability (Show measurement, test conditions, and source)

Source value: 0.71
Score: 0.71
Metric: aggregate predictability
Unit: rating
Benchmark version: final leak-cleaned public validation set
Category: agentic
Task: predictability
Task label: Predictability
Direction: Higher is better
Comparison cohort: hal-gaia-reliability-hal-reliability-predictability
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-1c53c174caef. Source payload hash: 1c53c174caef16e9fce637ae32349d954da5c8a7493eb5ccbfc1b3b74b7df1b2. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.

Source Princeton HAL

GAIA Reliability: Reliability (Show measurement, test conditions, and source)

Source value: 0.78
Score: 0.78
Metric: aggregate reliability
Unit: rating
Benchmark version: final leak-cleaned public validation set
Category: agentic
Task: reliability
Task label: Reliability
Direction: Higher is better
Comparison cohort: hal-gaia-reliability-hal-reliability-reliability
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-8d19bbb49250. Source payload hash: 8d19bbb4925070a4e6ec390b4d5684ae50db13a01227057bc90bb40f1a762e09. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.

Source Princeton HAL

GAIA Reliability: Robustness (Show measurement, test conditions, and source)

Source value: 0.91
Score: 0.91
Metric: aggregate robustness
Unit: rating
Benchmark version: final leak-cleaned public validation set
Category: agentic
Task: robustness
Task label: Robustness
Direction: Higher is better
Comparison cohort: hal-gaia-reliability-hal-reliability-robustness
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-1796d18fe25c. Source payload hash: 1796d18fe25c8013919dfe86d7063843be59e912ef58bfb042e346d61d24613e. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.

Source Princeton HAL

GAIA Reliability: Safety (Show measurement, test conditions, and source)

Source value: 1
Score: 1
Metric: aggregate safety
Unit: rating
Benchmark version: final leak-cleaned public validation set
Category: agentic
Task: safety
Task label: Safety
Direction: Higher is better
Comparison cohort: hal-gaia-reliability-hal-reliability-safety
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-c63a794d3d54. Source payload hash: c63a794d3d549f51d32f25a48655db8386502ffd23bb1bd44974e9db28f6bdc8. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.

Source Princeton HAL

GAIA Reliability: Accuracy (Show measurement, test conditions, and source)

Source value: 52.5
Score: 52.5
Metric: exact-match accuracy
Unit: %
Benchmark version: final leak-cleaned public validation set
Category: agentic
Task: overall
Task label: Accuracy
Direction: Higher is better
Comparison cohort: hal-gaia-reliability-hal-reliability-overall
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.. Source model ID: curated/gemini-2.5-pro. Source model name: Gemini 2.5 Pro. Provider reported by source: Google. Evaluator: Princeton HAL. Dataset type: public. Harness: HAL Reliability. Agent: HAL Reliability. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-5c16f4ffaaa5. Source payload hash: 5c16f4ffaaa5ac8a5c682da01aa3fab9655de1625348891876a58ad2be1d678f. Parser version: curated-v1. Imported at: 2026-09-29
Comparison methodology: 165 GAIA tasks with repeated runs and perturbations. HAL does not publish cost for this evaluation.

Source Princeton HAL

Page 1 of 8

Predecessor and successor

Sources and data date

Type	Evidence and data date
Speed	Google. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Context window data (retrieved September 8, 2026) · Gemini 2.5 Pro API documentation · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Context window data (retrieved September 8, 2026) · Gemini 2.5 Pro API documentation · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	parameters-billions Original wording Google does not publish a parameter count on the Gemini API model page.
Not found in the inspected sources	active-parameters-billions Original wording Google does not publish active parameter counts for Gemini API models.
Additional source	Model metadata
Additional source	Knowledge cutoff data
Additional source	Aider (retrieved September 2, 2026)
Additional source	DeepResearch Bench (retrieved August 9, 2026)
Additional source	Google DeepMind (retrieved August 9, 2026)
Additional source	Princeton HAL (retrieved August 6, 2026)
Additional source	Princeton HAL (retrieved August 5, 2026)
Additional source	LongBench (retrieved September 2, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Google DeepMind (retrieved September 8, 2026) · Gemini 2.5 Pro model card · Editorial description reviewed October 2, 2026
Additional source	Model metadata (retrieved September 8, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0
Additional source	Google, "Gemini 3 for developers" (2026-09-22)

Gemini 2.5 Pro

Specifications and access

Published benchmarks

Aider Polyglot

Knowledge

FACTS Benchmark Suite

Agent tasks

GAIA Reliability

GAIA Reliability

Recorded measurement details

Our tests

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date