Gemma 4 E2B (Non-reasoning)

Gemma 4 E2B (Non-reasoning)

Google · Released Apr 2, 2026
Intelligence #521 / 620
16.8 our score
AA Index #307 / 395
6.4 Artificial Analysis
Input Price
– Not priced
Output Price
– Not priced
Context
– Not reported

Analysis Summary

Gemma 4 E2B is an ultra-lightweight model from Google, with reasoning, instruction-following and agentic benchmark scores well below larger models in its class.

It is not suited to business-critical tasks such as coding, complex analysis or client-facing writing, but its small footprint could support very simple, high-volume classification or on-device tasks where cost and speed outweigh accuracy needs.

Businesses should treat this as an edge-deployment or prototyping tool rather than a production content or coding assistant.

Assessed July 25, 2026

Editorial notes

Gemma 4 E2B is a very small, low-cost model from Google with limited reasoning and instruction-following ability, suited only to trivial tasks.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Gemma 4 E2B is a very small, low-cost model from Google with limited reasoning and instruction-following ability, suited only to trivial tasks.

#521 of 620 overall

Benchmark scores

GPQA Diamond 40.5%
HLE 4.5%
SciCode 20.4%
TerminalBench Hard 2.3%
τ²-Bench 22.2%
IFBench 33.6%
LCR 15%

Magenta = intelligence Ā· Ink = technical/agentic Ā· Cyan = content & long-context Ā· Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

6.4 Intelligence IndexĀ·12.2 Agentic Index

How Gemma 4 E2B (Non-reasoning) compares

Gemma 4 E2B (Non-reasoning) ranks #307 of 395 AI models we track for overall intelligence, #239 of 302 for agentic tasks. Gemma 4 E2B (Non-reasoning) is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 16% of models #521
worst in fieldmedianbest in field
Price vs frontier peers Ā· $ per 1M tokens
Gemma 4 E2B (Non-reasoning) $0.00 in $0.00 out
Anthropic: Claude Fable 5 $10.00 in $50.00 out
Anthropic: Claude Opus 4.8 $5.00 in $25.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input Ā· light bar = output, scaled to the priciest peer.

Context window vs peers Ā· tokens
Gemma 4 E2B (Non-reasoning) 0

1M tokens ā‰ˆ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence1.4Technical1.2Value0Content2.5
Performance profile

Strongest on content. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Gemma 4 E2B (Non-reasoning)

How much does Gemma 4 E2B (Non-reasoning) cost?

Gemma 4 E2B (Non-reasoning) is currently available for free via OpenRouter.

Who created Gemma 4 E2B (Non-reasoning)?

Gemma 4 E2B (Non-reasoning) is developed by Google and was released on April 2, 2026.