Gemma 4 E2B (Reasoning)

Gemma 4 E2B (Reasoning)

Google · Released Apr 2, 2026
Intelligence #540 / 650
19.3 our score
AA Index #250 / 401
9.7 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Gemma 4 E2B is a compact reasoning variant from Google's Gemma family. Its intelligence and agentic scores are low relative to current flagship models, though it shows reasonable instruction-following performance for its size.

This makes it a candidate for lightweight, cost-sensitive deployments such as simple chat assistants or structured data tasks, rather than complex coding or long-document analysis.

Businesses needing a small, efficient model for narrow tasks could deploy it, but should not expect strong performance on demanding reasoning or coding workloads.

Assessed July 29, 2026

Editorial notes

Gemma 4 E2B (Reasoning) from Google is a small reasoning-focused model with limited overall capability but usable instruction following.

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

DFO Verdict

Gemma 4 E2B (Reasoning) from Google is a small reasoning-focused model with limited overall capability but usable instruction following.

#540 of 650 overall

Benchmark scores

GPQA Diamond 43.3%
HLE 4.8%
SciCode 20.9%
TerminalBench Hard 3%
τ²-Bench 20.8%
IFBench 38%
LCR 15%

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

9.7 Intelligence Index·7.2 Coding Index·1.5 Agentic Index

How Gemma 4 E2B (Reasoning) compares

Gemma 4 E2B (Reasoning) ranks #250 of 401 AI models we track for overall intelligence, #161 of 176 for coding, #138 of 157 for agentic tasks. Gemma 4 E2B (Reasoning) is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 17% of models #540
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Gemma 4 E2B (Reasoning) $0.00 in $0.00 out
Anthropic: Claude Fable 5 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out
Anthropic: Claude Opus 4.8 $5.00 in $25.00 out

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

Context window vs peers · tokens

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

Intelligence1.7Technical1.2Value0Content3.5
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 (Reasoning)

How much does Gemma 4 E2B (Reasoning) cost?

Gemma 4 E2B (Reasoning) is currently available for free via OpenRouter.

Is Gemma 4 E2B (Reasoning) good for coding?

On our coding benchmark index, Gemma 4 E2B (Reasoning) ranks #161 of 176 models, placing it in the broader range of the field for code generation and debugging.

Who created Gemma 4 E2B (Reasoning)?

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

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.