Models / Gemma 4 E4B

Google

Gemma 4 E4B

Gemma 4 E4B trails most of the field on what it has been measured on; it is not on sale through OpenRouter, so it is here for reference.

Results 16 Nov 2026 · 27 results · 2 sources

Price per million tokens
Not available through OpenRouter
Speed
32 tokens a second; on its test prompt the answer starts after 0.4 s, thinking time included
Artificial Analysis, on its usual API, at no reasoning; 28–32 across 2 settings
Intelligence Index
8.9
Artificial Analysis; 7.5–8.9 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Google, based in the US
Weights not published
Released
3 Apr 2026 (Artificial Analysis)

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 146th of 186Claude Opus 5.5 – – 66th of 66Nemotron 3.5 Super VL
Models with similar intelligence sets this group – – 17th of 17gpt-oss-20b
Models writing under 50 tokens a second 9th of 10MiMo-V2.6-Pro – – sets this group
Models from developers based in the US 73rd of 93Claude Opus 5.5 – – 34th of 34Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 149th of 160 available
BenchmarkGemma 4 E4BRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 108 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 1.9% 104th of 108 Claude Fable 5.1 91.4%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 153rd of 188 available
BenchmarkGemma 4 E4BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 8.9 146th of 186 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 4.8% 152nd of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 57.6% 138th of 169 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 167th of 170 available
BenchmarkGemma 4 E4BRank among availableBest available
UGI LeaderboardUGI: writing score · reported 21.6 122nd of 125 Gemini 3.8 Flash 78.6
  • Arena (formerly LMArena): has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers Not measured
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Gemma 4 E4B, Intelligence Index 8.9. "Similar intelligence" means within 4 points or better.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Gemma 4 E4Bgpt-oss-20b
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Claude Fable 5.2
leads overall
Gemini 4 Argon
Google's best other model
Price per million tokens – $0.06$8.00$16.00$4.00
Tokens a second 32 27796––
Intelligence Index 8.9 10.057.6–52.6
Spring Prompt overall – –829072
Rank among available models, by use case
Product listings – –13th5th11th
Decks from an analysis – –7th4th23rd
User surveys – –4th1st15th
Marketing planning – –9th1st13th
Agents and tool use 149th of 160 129th3rd–5th
Professional work – –3rd––
Reasoning and knowledge 153rd of 188 132nd1st–4th
Writing 167th of 170 155th5th–1st
Sticking to the facts – –3rd–1st
Speed under pressure – ––8th26th

Shaded figures are better than Gemma 4 E4B's. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), in the bottom quarter for agents and tool use, reasoning and knowledge, and writing.

Every result

27 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 21 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 8.9 340 of 413 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 7.5 363 of 413 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 57.6% 302 of 360 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 54.9% 310 of 360 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 3.8% 389 of 419 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 4.8% 350 of 419 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 44.2% 174 of 288 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 40.5% 201 of 288 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 32.0% 336 of 407 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 24.0% 353 of 407 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 28.0 135 of 137 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 31.7 134 of 137 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 24.4% 199 of 205 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 1.9% 179 of 188 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 8.3% 204 of 282 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 7.6% 208 of 282 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 71.9 125 of 137 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 0.43 5 of 137 Gemma 4 E4B (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 20.8% 253 of 286 Gemma 4 E4B 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 26.0% 230 of 286 Gemma 4 E4B (no reasoning) 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 15.0% 127 of 379 Gemma 4 E4B 25 May 2026
UGI: requested-length error% off the requested word count, lower is better 10.0% 89 of 379 Gemma 4 E4B (channel-thought-prefill reasoning) 25 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.29 350 of 379 Gemma 4 E4B 25 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.30 336 of 379 Gemma 4 E4B (channel-thought-prefill reasoning) 25 May 2026
UGI: writing scorescore out of 100, higher is better 20.2 340 of 379 Gemma 4 E4B 25 May 2026
UGI: writing scorescore out of 100, higher is better 21.6 334 of 379 Gemma 4 E4B (channel-thought-prefill reasoning) 25 May 2026

Not shown: Not other format limits such as character counts or bullet counts.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.