Language modelActive

Gemini 2.5 Flash-Lite

Google

Released: July 22, 2025
Data date: September 8, 2026
Predecessor: Gemini 2.0 Flash-Lite Preview (Official documentation)
Successor: Gemini 3.1 Flash-Lite

Benchmark-Meta-Score: Unavailable
Fewer than eight test series
Speed: 325.9 tokens/s
Output throughput
Price: $0.1 · $0.4
Input · Output / 1M tokens
Input: Text, Image, Audio, Video
Output: Text

What is new about Gemini 2.5 Flash-Lite is the combination of stable GA availability and a now-restricted access policy. Google continues serving the API to users who previously used the 2.5 models, while recommending newer models for new projects. The documented predecessor is Gemini 2.0 Flash-Lite Preview.

Google does not publish a parameter count. Its model card describes Gemini 2.5 Flash-Lite as a sparse mixture-of-experts model with native multimodal support for text, vision, and audio.

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-flash-liteSource
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	2025-07-22Source
Knowledge cutoff	2025-01Source
Capabilities	function calling, structured outputs, search grounding, Google Maps grounding, URL context, code execution, file searchSource
General availability	2025-07-22 (General availability (GA).)Source

Benchmark meta-analysis

Overall and area scores

These Gradually indexes place selected published measurements on a 0 to 100 scale. They are not accuracy percentages and do not guarantee results in your application.

Retrieval dates of the sources used 2026-10-15 - 2026-10-15

Overall index

Not enough independent results for a score yet

An overall score needs at least eight test series.

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Test series: 3
Test families: 2 / 65
Sources: 1
Share of the fixed test panel (informative): 6 %

Health

Index below 1 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 0.0
95% interval: 0.0 to 1.6
Test series: 2
Test families: 2 / 3
Sources: 1
Share of the fixed test panel (informative): 67 %

Education

Index below 1 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 0.0
95% interval: 0.0 to 0.0
Test series: 1
Test families: 1 / 2
Sources: 1
Share of the fixed test panel (informative): 50 %

Documented method · Included test families and measurements

Method version: benchmark-meta-score-v3

The index includes active measurements from reviewed primary sources when at least five models are compared in the same documented comparison slice across dataset, harness, agent, tools, and trial count. Each benchmark series and evaluator contributes one shared setup slice from the newest capture. When one source and series include several explicitly documented reasoning tiers, the highest documented tier (none through max) is selected, never the best result value. The explicit source label “Non-reasoning” is treated as none. Unknown or ambiguous tiers exclude the model from that series. Within each series, percentages and rates are logit-transformed, other units stay unchanged, and all values are then standardized. A one-factor model then estimates one shared strength per model and, per series, how sharply it separates the models. Area scores move away from that strength only as far as the model's own results in the area support. The overall score weights the core areas at 75% and finance, law and health at 25%. It requires at least eight test series from two sources and three areas. The 0 to 100 scale refers to a fixed reference group of 29 language models whose average sits at 50.

Published model-specific parameters can differ. This is not a controlled experiment; comparisons with such differences are marked provisional.

Unmeasured series are not entered as zero. Where a model has no own results in a core area, its overall strength stands in, and the note “estimated without own results in …” names the area. Fewer test series lead to a larger standard error.

The 95% interval follows from the standard error of 200 recalculations with randomly redrawn test families. It describes how precisely the recorded test series determine the value. It is no prediction for future tasks or for later recalculations with other participants.

The source count is not a count of independent experiments.

OECD handbook on composite indicators

All 3 test families and 3 of 3 raw measurements are listed here. The complete calculation for every model is available in the JSON export.

Test family: MedCode
Health · Mean rank percentile of the family: 1.5 / 100
Family weight in the fixed test panel (informative): 2.78 % · Coverage of this test family: 100 %
- Vals AI
  Published configurations differ within this cohort.
  Measurement:
  vals-medcode
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  2.78 %
  Raw value:
  27.115 %
  Metric:
  accuracy
  Version:
  1
  Participating models:
  68
  Rank percentile within the cohort:
  1.5 %
  Retrieved:
  2026-10-15
  Comparison cohort:
  vals-medcode:1:overall
  Documented comparison setup
  Publication cohort:
  vals-medcode:1:overall
  Dataset type:
  private
  Setup and model parameters
  Temperature: 1. Maximum output tokens: 30000
  Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 5.746. Standard error: 1.843. Cost per task in USD: 0.001342. Source ID: vals-ai. Evidence capture ID: vals-medcode-2026-10-15-988a6ae1e07e. Source payload hash: 988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Test family: MedScribe
Health · Mean rank percentile of the family: 17.6 / 100
Family weight in the fixed test panel (informative): 2.78 % · Coverage of this test family: 100 %
- Vals AI
  Published configurations differ within this cohort.
  Measurement:
  vals-medscribe
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  2.78 %
  Raw value:
  72.832 %
  Metric:
  accuracy
  Version:
  1
  Participating models:
  69
  Rank percentile within the cohort:
  17.6 %
  Retrieved:
  2026-10-15
  Comparison cohort:
  vals-medscribe:1:overall
  Documented comparison setup
  Publication cohort:
  vals-medscribe:1:overall
  Dataset type:
  private
  Setup and model parameters
  Temperature: 1. Maximum output tokens: 30000
  Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 4.847. Standard error: 1.982. Cost per task in USD: 0.001211. Source ID: vals-ai. Evidence capture ID: vals-medscribe-2026-10-15-271fc122ddc2. Source payload hash: 271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0. Parser version: vals-astro-v3. Imported at: 2026-10-15
Test family: SAGE
Education · Mean rank percentile of the family: 3.4 / 100
Family weight in the fixed test panel (informative): 0 % · Coverage of this test family: 100 %
- Vals AI
  Published configurations differ within this cohort.
  Measurement:
  vals-sage
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  0 %
  Raw value:
  27.533 %
  Metric:
  accuracy
  Version:
  1
  Participating models:
  59
  Rank percentile within the cohort:
  3.4 %
  Retrieved:
  2026-10-15
  Comparison cohort:
  vals-sage:1:overall
  Documented comparison setup
  Publication cohort:
  vals-sage:1:overall
  Dataset type:
  private
  Setup and model parameters
  Temperature: 1. Maximum output tokens: 30000
  Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 13.781. Standard error: 3.124. Cost per task in USD: 0.000929. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15

Benchmark sources at a glance

Each evaluator measures different capabilities under its own conditions. Test series, composite indices and their components stay separate. The detailed results below retain their scales, configurations and source dates.

Evaluator	Test series	Composite indices	Recorded active measurements
Artificial Analysis	3	1	16
Vals AI	3	0	7

Coverage is not a quality ranking. Overlapping tests and multiple settings do not count as independent experiments. Vendor claims, historical and disputed results are excluded from this overview and remain labelled in the detailed evidence.

6 measurements from these sources still lack a verified test-family identity and do not increase the test-series count.

Published benchmarks

Health

MedCode

Overall

1.Gemini 2.5 Pro50.59%

2.GLM-5.240.77%

3.Qwen 3.8 Max 090240.67%

4.Claude Sonnet 4.540.57%

5.Qwen 3.7 Max38.75%

6.Gemini 2.5 Flash-Lite27.12%

7.Llama 4 Scout23.31%

higher is betterAs of October 15, 2026Scale: 0% - 100%

Source: Vals AI

gradually.ai

Methodology and context

Comparison cohort: vals-medcode:1:overall
Metric: accuracy
Scale: 0-100
Participants: 7
Methodology and context: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 5.746. Standard error: 1.843. Cost per task in USD: 0.001342. Source ID: vals-ai. Evidence capture ID: vals-medcode-2026-10-15-988a6ae1e07e. Source payload hash: 988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c. Parser version: vals-astro-v3. Imported at: 2026-10-15

Source: Vals AI

MedScribe

Overall

1.Qwen 3.8 Max 090284.95%

2.Claude Sonnet 4.584.52%

3.GLM-5.283.53%

4.Qwen 3.7 Max79.4%

5.Gemini 2.5 Pro73.55%

6.Gemini 2.5 Flash-Lite72.83%

7.Llama 4 Scout50.59%

higher is betterAs of October 15, 2026Scale: 0% - 100%

Source: Vals AI

gradually.ai

Methodology and context

Comparison cohort: vals-medscribe:1:overall
Metric: accuracy
Scale: 0-100
Participants: 7
Methodology and context: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 4.847. Standard error: 1.982. Cost per task in USD: 0.001211. Source ID: vals-ai. Evidence capture ID: vals-medscribe-2026-10-15-271fc122ddc2. Source payload hash: 271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0. Parser version: vals-astro-v3. Imported at: 2026-10-15

Source: Vals AI

Education

SAGE

Sub-task	Gemini 2.5 Flash-Lite (This model)	Gemini 2.5 Pro	Qwen 3.8 Max 0902	Qwen 3.7 Plus	Claude Sonnet 4.5	Llama 4 Scout	Mistral Large 3
Automata	33.33%	43.65% (best value in this row)	39.68%	32.54%	20.24%	14.68%	11.91%
Linear Algebra	28.63%	51.94%	69.64% (best value in this row)	51.88%	51.42%	61.25%	44.42%
Overall	27.53%	41.92%	51.25% (best value in this row)	39.25%	32.88%	34.83%	24.6%
Partial Differential Equations	20.64%	30.16%	44.44% (best value in this row)	33.33%	26.98%	28.57%	17.46%

higher is betterAs of October 15, 2026Source: Vals AIbars scaled within each row, not across rows

Methodology and context

Metric: accuracy

SAGE

Calculus

1.Qwen 3.8 Max 090271.91%

2.Gemini 2.5 Pro70.68%

3.Claude Opus 4.558.33%

4.Claude Sonnet 4.537.65%

5.Gemini 2.5 Flash-Lite13.89%

6.Llama 4 Scout5.25%

7.Mistral Large 30%

higher is betterAs of October 15, 2026Scale: 0% - 100%

Source: Vals AI

gradually.ai

Methodology and context

Comparison cohort: vals-sage:1:calculus
Metric: accuracy
Scale: 0-100
Participants: 7
Methodology and context: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 13.337. Standard error: 4.298. Cost per task in USD: 0.001699. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15

Source: Vals AI

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

IFBench: Overall (Show measurement, test conditions, and source)

Source value: 31.496598639455797
Score: 31.496598639455797
Metric: IFBench prompt-level loose accuracy (pass@1)
Unit: %
Benchmark version: AA test set: 294 questions
Category: general
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:tokens=0:suffix=Non-reasoning
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-19
Methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Non-reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite, UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91, reasoning=false, source reasoning-token configuration budget=0, suffix=Non-reasoning). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/1d81aa1c-64c8-442a-9c41-81b37e407b91/gemini-2-5-flash-lite/gemini-2-5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Model snapshot: Gemini 2.5 Flash-Lite (Non-reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: Non-reasoning. Score display: 31.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
Comparison methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Non-reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite, UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91, reasoning=false, source reasoning-token configuration budget=0, suffix=Non-reasoning). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: Non-reasoning
Context: The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.

Source Artificial Analysis

IFBench: Overall (Show measurement, test conditions, and source)

Source value: 49.8639455782313
Score: 49.8639455782313
Metric: IFBench prompt-level loose accuracy (pass@1)
Unit: %
Benchmark version: AA test set: 294 questions
Category: general
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:reasoning:tokens=0:suffix=Reasoning
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-19
Methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite-reasoning, UUID f4e8194a-d0e6-48eb-92be-4307de5aeeec, reasoning=true, source reasoning-token configuration budget=0, suffix=Reasoning). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/f4e8194a-d0e6-48eb-92be-4307de5aeeec/gemini-2-5-flash-lite/gemini-2-5-flash-lite-reasoning. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Model snapshot: Gemini 2.5 Flash-Lite (Reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: reasoning enabled. Reasoning effort: Reasoning. Score display: 49.9%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
Comparison methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite-reasoning, UUID f4e8194a-d0e6-48eb-92be-4307de5aeeec, reasoning=true, source reasoning-token configuration budget=0, suffix=Reasoning). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: reasoning enabled. Reasoning effort: Reasoning
Context: The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.

Source Artificial Analysis

MMMU-Pro: Overall (Show measurement, test conditions, and source)

Source value: 53.9884393063584
Score: 53.9884393063584
Metric: pass@1 accuracy
Unit: %
Benchmark version: AA cohort: 1,730 questions
Category: multimodal
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:non-reasoning:tokens=0:suffix=Non-reasoning
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-19
Methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Non-reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite, UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91, reasoning=false, source reasoning-token configuration budget=0, suffix=Non-reasoning). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/1d81aa1c-64c8-442a-9c41-81b37e407b91/gemini-2-5-flash-lite/gemini-2-5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Model snapshot: Gemini 2.5 Flash-Lite (Non-reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: non-reasoning. Reasoning effort: Non-reasoning. Score display: 54.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
Comparison methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Non-reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite, UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91, reasoning=false, source reasoning-token configuration budget=0, suffix=Non-reasoning). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: non-reasoning. Reasoning effort: Non-reasoning
Context: The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.

Source Artificial Analysis

MMMU-Pro: Overall (Show measurement, test conditions, and source)

Source value: 58.2080924855491
Score: 58.2080924855491
Metric: pass@1 accuracy
Unit: %
Benchmark version: AA cohort: 1,730 questions
Category: multimodal
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:reasoning:tokens=0:suffix=Reasoning
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-19
Methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite-reasoning, UUID f4e8194a-d0e6-48eb-92be-4307de5aeeec, reasoning=true, source reasoning-token configuration budget=0, suffix=Reasoning). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/f4e8194a-d0e6-48eb-92be-4307de5aeeec/gemini-2-5-flash-lite/gemini-2-5-flash-lite-reasoning. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Model snapshot: Gemini 2.5 Flash-Lite (Reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Reasoning effort: Reasoning. Score display: 58.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
Comparison methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite-reasoning, UUID f4e8194a-d0e6-48eb-92be-4307de5aeeec, reasoning=true, source reasoning-token configuration budget=0, suffix=Reasoning). This configured value is not measured token consumption. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Reasoning effort: Reasoning
Context: The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.

Source Artificial Analysis

AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)

Source value: 15.433333333333332
Score: 15.433333333333332
Metric: AA-Omniscience Accuracy
Unit: %
Benchmark version: AA Omniscience diagnostic
Category: knowledge
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:non-reasoning:tokens=0:suffix=Non-reasoning
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-19
Methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Non-reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite, UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91, reasoning=false, source reasoning-token configuration budget=0, suffix=Non-reasoning). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Source model ID: artificial-analysis/1d81aa1c-64c8-442a-9c41-81b37e407b91/gemini-2-5-flash-lite/gemini-2-5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Model snapshot: Gemini 2.5 Flash-Lite (Non-reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: non-reasoning. Reasoning effort: Non-reasoning. Score display: 15.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
Comparison methodology: Exact AA configuration: Gemini 2.5 Flash-Lite (Non-reasoning) (release gemini-2-5-flash-lite, row gemini-2-5-flash-lite, UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91, reasoning=false, source reasoning-token configuration budget=0, suffix=Non-reasoning). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: non-reasoning. Reasoning effort: Non-reasoning
Context: This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.

Source Artificial Analysis

Recorded measurement details

MedCode: Overall (Show measurement, test conditions, and source)

Source value: 27.115
Score: 27.115
Metric: accuracy
Unit: %
Benchmark version: 1
Category: health
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-medcode:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 5.746. Standard error: 1.843. Cost per task in USD: 0.001342. Source ID: vals-ai. Evidence capture ID: vals-medcode-2026-10-15-988a6ae1e07e. Source payload hash: 988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

MedScribe: Overall (Show measurement, test conditions, and source)

Source value: 72.832
Score: 72.832
Metric: accuracy
Unit: %
Benchmark version: 1
Category: health
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-medscribe:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-13. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 4.847. Standard error: 1.982. Cost per task in USD: 0.001211. Source ID: vals-ai. Evidence capture ID: vals-medscribe-2026-10-15-271fc122ddc2. Source payload hash: 271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

SAGE: Automata (Show measurement, test conditions, and source)

Source value: 33.334
Score: 33.334
Metric: accuracy
Unit: %
Benchmark version: 1
Category: education
Task: automata
Task label: Automata
Direction: Higher is better
Comparison cohort: vals-sage:1:automata
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 10.448. Standard error: 6.023. Cost per task in USD: 0.000876. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

SAGE: Linear Algebra (Show measurement, test conditions, and source)

Source value: 28.629
Score: 28.629
Metric: accuracy
Unit: %
Benchmark version: 1
Category: education
Task: linear_algebra
Task label: Linear Algebra
Direction: Higher is better
Comparison cohort: vals-sage:1:linear_algebra
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 18.12. Standard error: 5.077. Cost per task in USD: 0.000791. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

SAGE: Overall (Show measurement, test conditions, and source)

Source value: 27.533
Score: 27.533
Metric: accuracy
Unit: %
Benchmark version: 1
Category: education
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-sage:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 13.781. Standard error: 3.124. Cost per task in USD: 0.000929. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

SAGE: Partial Differential Equations (Show measurement, test conditions, and source)

Source value: 20.635
Score: 20.635
Metric: accuracy
Unit: %
Benchmark version: 1
Category: education
Task: PDEs
Task label: Partial Differential Equations
Direction: Higher is better
Comparison cohort: vals-sage:1:PDEs
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 12.776. Standard error: 5.078. Cost per task in USD: 0.001121. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

SAGE: Calculus (Show measurement, test conditions, and source)

Source value: 13.889
Score: 13.889
Metric: accuracy
Unit: %
Benchmark version: 1
Category: education
Task: calculus
Task label: Calculus
Direction: Higher is better
Comparison cohort: vals-sage:1:calculus
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-10-15
Methodology: Source model ID: google/gemini-2.5-flash-lite. Source model name: Gemini 2.5 Flash-Lite. Provider reported by source: Google. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-08. Temperature: 1. Maximum output tokens: 30000. Latency in seconds: 13.337. Standard error: 4.298. Cost per task in USD: 0.001699. Source ID: vals-ai. Evidence capture ID: vals-sage-2026-10-15-cc5fb3fecdb0. Source payload hash: cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c. Parser version: vals-astro-v3. Imported at: 2026-10-15
Comparison methodology: Temperature: 1. Maximum output tokens: 30000

Source Vals AI

Page 1 of 3

Predecessor and successor

Predecessor: Gemini 2.0 Flash-Lite Preview (Official documentation)
Official documentation
Model lineage evidence
The lifecycle table lists `gemini-2.0-flash-lite-preview` (and its dated snapshot `gemini-2.0-flash-lite-preview-02-05`) as discontinued December 9, 2025 with recommended replacement `gemini-2.5-flash-lite`.
Google Gemini API model deprecations and lifecycle table (2026-09-19)
Later model generation: Gemini 3.1 Flash-Lite
Next generation in the directory
Model lineage evidence
The table gives the GA `gemini-2.5-flash-lite` id itself no shutdown date or replacement (still active); only its dated preview snapshot `gemini-2.5-flash-lite-preview-09-2025` is marked replaced by `gemini-3.1-flash-lite`, so this Flash-Lite-tier link is recorded as nearest-profile rather than a directly documented GA-to-GA succession.
Google Gemini API model deprecations and lifecycle table (2026-09-19)

Sources and data date

Type	Evidence and data date
Speed	Google, Non-reasoning. 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 Flash-Lite 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 Flash-Lite 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	Artificial Analysis (retrieved October 19, 2026)
Additional source	Artificial Analysis (retrieved October 19, 2026)
Additional source	Artificial Analysis (retrieved October 19, 2026)
Additional source	Vals AI (retrieved October 15, 2026)
Additional source	Vals AI (retrieved October 15, 2026)
Additional source	Vals AI (retrieved October 15, 2026)
Additional source	Google DeepMind (retrieved September 8, 2026) · Gemini 2.5 Flash-Lite 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	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0

Gemini 2.5 Flash-Lite

Specifications and access

Overall and area scores

Overall index

Health

Education

Test family: MedCode

Test family: MedScribe

Test family: SAGE

Benchmark sources at a glance

Published benchmarks

Health

MedCode

MedScribe

Education

SAGE

SAGE

Measurements without matching peer values

Recorded measurement details

Our tests

SVG short test

Gemini 2.5 Flash-Lite

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date