Model Profile

gemma-2b-it

Name: gemma-2b-it
Rating: 1.9 (52 reviews)
Author: google

4,096 ctxOpen weights

Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.

Identity

ID: google/gemma-2b-it

Author: google

Origin: huggingface_catalog

Arch: unknown

Benchmark Coverage

Scored use cases: 12

Avg confidence: 21.2%

Evidence points: 52

Raw rows: 9

Weighted rows: 6

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 75,098

Intelligence Profile

Dimension Breakdown

IQ0 benchmarks

No iq benchmarks found

Insufficient data

EQ1 benchmark

25.9%*

Accuracy0 benchmarks

No accuracy benchmarks found

Insufficient data

Creativity0 benchmarks

No creativity benchmarks found

Insufficient data

Based1 benchmark

40.5%*

* Low confidence — limited benchmark evidence for this dimension

2/5 dimensions scored · Last updated Apr 21, 2026

Benchmark Signals

Click through to the benchmark source behind this model profile.

LLM Trustworthy Leaderboard

fairness

4.6%

Normalized value 81.4% · confidence 100.0%

Strongest impact in Jailbreak resistance (eval)

llm_trustworthy_leaderboard.fairness · Mar 31, 2026

LLM Trustworthy Leaderboard

privacy

4.0%

Normalized value 83.1% · confidence 100.0%

Strongest impact in Jailbreak resistance (eval)

llm_trustworthy_leaderboard.privacy · Mar 31, 2026

LLM Trustworthy Leaderboard

adv

1.8%

Normalized value 40.5% · confidence 100.0%

Strongest impact in Jailbreak resistance (eval)

llm_trustworthy_leaderboard.adv · Mar 31, 2026

LLM Trustworthy Leaderboard

toxicity

1.5%

Normalized value 50.0% · confidence 100.0%

Strongest impact in Jailbreak resistance (eval)

llm_trustworthy_leaderboard.toxicity · Mar 31, 2026

EQ-Bench Leaderboard

eq_bench_score

1.1%

Normalized value 25.9% · confidence 100.0%

Strongest impact in Social post generation

eq_bench.eq_bench_score · Apr 1, 2026

Some fit rows have limited benchmark evidence.

7 of 12 scored use cases have low confidence or thin contributor coverage.

Coverage Diagnostics

actively scored

Use-Case Scores

Total Measurements

Weighted Measurements

Weighted Sources

Raw Source Coverage

llm_trustworthy_leaderboard 8eq_bench 1

Weighted Source Coverage

llm_trustworthy_leaderboard 5eq_bench 1

Best Use Cases for This Model

Use Case	Vertical	Score	Confidence	Evidence	Top Contributor
Jailbreak resistance (eval) use_case.security.jailbreak_resistance_eval	risk_eval	19.4%	29.8%	5	LLM Trustworthy Leaderboard: fairness
Scam and social engineering resistance (eval) use_case.security.scam_social_engineering_resistance_eval	risk_eval	19.4%	29.8%	5	LLM Trustworthy Leaderboard: fairness
Overrefusal (eval) use_case.security.overrefusal_eval	risk_eval	19.4%	29.8%	5	LLM Trustworthy Leaderboard: fairness
Refusal profile (eval) use_case.security.refusal_profile_eval	risk_eval	19.4%	29.8%	5	LLM Trustworthy Leaderboard: fairness
Crisis escalation protocol (eval) use_case.safety.crisis_escalation_protocol	risk_eval	19.4%	29.8%	5	LLM Trustworthy Leaderboard: fairness
Vulnerability-oriented code review use_case.cyber.vulnerability_review	cybersecurity	11.5%	17.7%	5	LLM Trustworthy Leaderboard: fairness
Disinformation and manipulation resistance (eval) use_case.security.disinformation_resistance_eval	risk_eval	10.3%	15.9%	5	LLM Trustworthy Leaderboard: fairness
Campaign brief use_case.mkt.campaign_brief	marketing_sales	8.6%	14.9%	3	LLM Trustworthy Leaderboard: fairness
Product positioning and messaging use_case.mkt.product_positioning	marketing_sales	8.6%	14.9%	3	LLM Trustworthy Leaderboard: fairness
Social post generation use_case.mkt.social_post_generation	marketing_sales	8.6%	14.9%	3	LLM Trustworthy Leaderboard: fairness
Security incident triage use_case.cyber.incident_triage	cybersecurity	8.2%	12.6%	5	LLM Trustworthy Leaderboard: fairness
Personalized sales outreach use_case.mkt.sales_outreach_personalized	marketing_sales	8.1%	14.1%	3	LLM Trustworthy Leaderboard: fairness