Gemma 4 E4B

Gemma 4 E4B is a reasoning model from Google in the Gemma 4 family. 14 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.29.5 ±5.3
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
24.7
CodingCode writing and repair.
25.6
ReasoningLogic problems and puzzles.
35.0
MultimodalTasks with images and text.
29.9
KnowledgeFacts and expert knowledge.
29.4
MultilingualTasks in many languages.
36.0
InstructionTasks with strict rules in the prompt.
34.0
MathMath problems.
N/A

Results

14 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Massive Multitask Language Understanding ProfessionalKnowledge69.4%29.8Yubo Wang et al.
Graduate-Level Google-Proof Q&AKnowledge58.6%32.3David Rein et al.
Artificial Analysis GPQA DiamondKnowledge57.6%27.6Artificial Analysis
Artificial Analysis MMMU-ProMultimodal51.4%29.9Artificial Analysis
Artificial Analysis IFBenchInstruction44.2%34.0Artificial Analysis
EuroEval DutchMultilingual33.2%43.8EuroEval
Artificial Analysis Long Context ReasoningReasoning32.0%30.4Artificial Analysis
EuroEval FrenchMultilingual30.1%39.9EuroEval
EuroEval SwedishMultilingual29.2%38.8EuroEval
EuroEval PortugueseMultilingual27.6%36.8EuroEval
EuroEval ItalianMultilingual26.4%35.2EuroEval
EuroEval PolishMultilingual25.2%33.8EuroEval
EuroEval SpanishMultilingual23.6%31.8EuroEval
EuroEval GermanMultilingual21.7%29.5EuroEval
τ²-Bench Tool-Agent-User EvaluationAgentic20.8%13.8Victor Barres et al.
Artificial Analysis Coding IndexCoding9.4%25.6Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge8.9%33.5Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge8.6%24.5Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge3.8%28.7Artificial Analysis
Critical Physics TasksReasoning0.6%39.6Artificial Analysis
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis

14 benchmarks count, from 21 of 21 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsEuroEval, collected directlyMIT — the leaderboard site and its CSV routes are in the licensed repository

More from Google

Gemini 3.7 Flash72.3Gemini 3.8 Flash72.1Gemini 3.5 Flash67.3Gemini 3.6 Flash66.8Gemini 3.1 Pro64.7