Data as of November 13, 2026 · How the score is built

Gemma 4 E2B

Name: Gemma 4 E2B
Author: Google

EstablishedOpen WeightReasoning

Decision readingGemma 4 E2B scores 23.8 out of 100 and ranks #200 of 215. This profile shows 6 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #117. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.

Email me when its price, rank or availability changes.

Find alternatives Compare Gemma 4 E2B

Capability

23.8/100

field median 49.4#200 of 215 ranked models

Public

#200of 215

Verified —

Price

Self-hosted; infrastructure cost varies

input median $0.60No comparable first-party hosted token rate

Speed

Not measured

field median 92 tok/sTime to first token not measured

Context

128Ktokens

field median 256,000Maximum output length is tracked separately

Decision snapshot

Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.

Strongest published evidence

Instruction Following ranks #117. A well-rounded choice across a range of tasks.

Validate before choosing

6 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 6 displayable benchmark rows

Is Gemma 4 E2B right for your job?

Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.

Where Gemma 4 E2B ranks by benchmark score:

Emails, resumes, and everyday writing· #73 of 100

Describe your job

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
Category	Score	Rank	Percentile	Weight	Benchmarks	Evidence
AgenticWeight 22%0 benchmarksNot measured	Not measured	Not ranked	Not available	22%	0 benchmarks	Not measured
CodingRank #152 of 162Percentile 6thWeight 20%1 benchmarkVerified	13.6	#152 of 162	6th	20%	1 benchmark	Verified
ReasoningRank #150 of 160Percentile 6thWeight 17%1 benchmarkVerified	18.6	#150 of 160	6th	17%	1 benchmark	Verified
MultimodalRank Not rankedWeight 12%2 benchmarksVerified	14.3	Not ranked	Not available	12%	2 benchmarks	Verified
KnowledgeRank #168 of 180Percentile 7thWeight 12%2 benchmarksReported	25.1	#168 of 180	7th	12%	2 benchmarks	Reported
MultilingualWeight 7%0 benchmarksNot measured	Not measured	Not ranked	Not available	7%	0 benchmarks	Not measured
Inst. FollowingRank #117 of 157Percentile 26thWeight 5%Not listedUnlisted sources	43.8	#117 of 157	26th	5%	Not listed	Unlisted sources
MathWeight 5%0 benchmarksNot measured	Not measured	Not ranked	Not available	5%	0 benchmarks	Not measured

6 of 919 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

AgenticNot measured
Coding1/1 verified
Reasoning1/1 verified
Multimodal2/2 verified
Knowledge0/2 verified
MultilingualNot measured
Inst. FollowingNot measured
MathNot measured

Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

AgenticNot eligible
Coding6th percentile
Reasoning6th percentile
MultimodalNot eligible
Knowledge7th percentile
MultilingualNot eligible
Instruction following26th percentile
MathNot eligible

The dashed outline is median of 6 nearest peers.

Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Every result says who ran the test. For this model, Google ran 3 of 6. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.

Overall rank

#200

of 215 on the leaderboard

Reported by Google

Shown with that label

Run by a benchmark

The benchmark’s own run

Independent runs

None yet

Carried from upstream

Not yet matched to its table

Coding1 row

Coding benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Benchmark	Score	Versus best verified row	Gap	Who ran it	Use in ranking
LiveCodeBench v6	44.0%	Best verified: Sakana Fugu-Ultra · 93.2%	Gap49.2 behind	Reported by Google Google Gemma 4 E2B Hugging Face model card	Shown only

Reasoning1 row

Reasoning benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Benchmark	Score	Versus best verified row	Gap	Who ran it	Use in ranking
MRCRv2	19.1%	Best verified: Sakana Fugu-Ultra · 93.6%	Gap74.5 behind	Reported by Google Google Gemma 4 E2B Hugging Face model card	Counts20% ref. weight

Multimodal2 rows

Multimodal benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Benchmark	Score	Versus best verified row	Gap	Who ran it	Use in ranking
MMMU-ProMassive Multi-discipline Multimodal Understanding Pro	44.2%	Best verified: GPT-6.1 Terra · 85.5%	Gap41.3 behind	Reported by Google Google Gemma 4 E2B Hugging Face model card	Counts30% ref. weight
ExtractBench (LlamaIndex)ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard)	51.85%	Best verified: GPT-6.1 Sol · 95.31%	Gap43.5 behind	Run by ExtractBench (LlamaIndex) ExtractBench leaderboard, November 12, 2026 snapshot (LlamaIndex)	Shown only

Knowledge2 rows

Knowledge benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Benchmark	Score	Versus best verified row	Gap	Who ran it	Use in ranking
MMLU-ProMassive Multitask Language Understanding Professional	60%	Best verified: Qwen3.7 Max · 89.6%	Gap29.6 behind	Carried from an upstream page Reported upstream source	Counts6% ref. weight
GPQAGraduate-Level Google-Proof Q&A	43.4%	Best verified: GPT-6 Astra · 96%	Gap52.6 behind	Carried from an upstream page Reported upstream source	Counts3% ref. weight

Outlined bars are lab-reported or carried from an upstream page. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.

How we label sources All 6 rows

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

Apr 2, 2026 · you are here
Gemma 4 E2B
Score 23.8 · Price not listed

E2b

Gemma 4 31B Gemma 4 31B · 28.8 Gemma 4 12B · 34.1 Gemma 4 26B A4B · 41.2 Gemma 4 E4B · 24.6

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

Weights model ID: google/gemma-4-E2BGoogle gemma-4-E2B model card
Context window: 128KGoogle Gemma 4 model documentation
Maximum output: Not sourced yet
Knowledge cutoff: Not sourced yet
Input modalities: text, image, audio, videoGoogle Gemma 4 model documentation
Output modalities: textGoogle Gemma 4 model documentation
Parameters: Not sourced yet

Availability: open weightsGoogle gemma-4-E2B model card
Cloud regions: Not tracked yet
Lifecycle: activeGoogle gemma-4-E2B model card
API capabilities: Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching: Not documented in the pricing record
Self-host: Open weights available; hardware estimate not sourced
Rate limits: Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

Gemma 4 E2B ranks #200 of 215 on the public leaderboard with a score of 23.75/100. It does not yet have enough sourced coverage for a verified position.

Gemma 4 E2B is a open weight model with a 128K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Official exact-value snapshot from Google's April 2, 2026 Gemma 4 model card and launch post. BenchLM maps only schema-equivalent results from the published table: MMLU Pro, GPQA Diamond, LiveCodeBench v6, MMMU Pro, and MRCR v2. AIME 2026, Codeforces, MMMLU, OmniDocBench 1.5, MATH-Vision, MedXPertQA MM, audio benchmarks, BigBench Extra Hard (no matching key), HLE, and Tau2 (average over 3) remain out-of-schema or unavailable for this model in the current weighted keys.

Gemma 4 E2B sits in the Gemma 4 family with Gemma 4 31B, Gemma 4 12B, Gemma 4 26B A4B, Gemma 4 E4B. 6 of 919 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Instruction Following at #117, while its lowest eligible position is Knowledge at #168. a well-rounded choice across a range of tasks.

Last updated November 13, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.

Estimate VRAM from known parameters

Questions

How does Gemma 4 E2B perform overall in AI benchmarks?

Gemma 4 E2B ranks #200 out of 215 models on the public BenchAlign leaderboard, with a score of 23.75/100. Its evidence status is Estimated, and this profile shows 6 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is Gemma 4 E2B good for knowledge and understanding?

Gemma 4 E2B ranks #168 out of 180 eligible models for knowledge and understanding, with a public category score of 25.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemma 4 E2B good for coding and programming?

Gemma 4 E2B ranks #152 out of 162 eligible models for coding and programming, with a public category score of 13.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemma 4 E2B good for reasoning and logic?

Gemma 4 E2B ranks #150 out of 160 eligible models for reasoning and logic, with a public category score of 18.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemma 4 E2B good for multimodal and grounded tasks?

Gemma 4 E2B has source-displayable benchmark coverage for multimodal and grounded tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Gemma 4 E2B open source?

Gemma 4 E2B is an open-weight model from Google. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Which sibling models are related to Gemma 4 E2B?

Gemma 4 E2B belongs to the Gemma 4 family. Related tracked variants include Gemma 4 31B, Gemma 4 12B, Gemma 4 26B A4B, plus 1 more. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does Gemma 4 E2B have full benchmark coverage on BenchLM?

No. Gemma 4 E2B currently has 16 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Gemma 4 E2B?

Gemma 4 E2B has a documented context window of 128K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Compare Gemma 4 E2B with every tracked model1032 comparisons