Gemma 4 E2B

Gemma 4 E2B 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 100.24.0 ±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.
24.1
ReasoningLogic problems and puzzles.
29.0
MultimodalTasks with images and text.
21.6
KnowledgeFacts and expert knowledge.
21.7
MultilingualTasks in many languages.
26.6
InstructionTasks with strict rules in the prompt.
27.7
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 ProfessionalKnowledge60.0%14.9Yubo Wang et al.
Artificial Analysis MMMU-ProMultimodal44.6%21.6Artificial Analysis
Graduate-Level Google-Proof Q&AKnowledge43.4%18.3David Rein et al.
Artificial Analysis GPQA DiamondKnowledge43.3%12.9Artificial Analysis
Artificial Analysis IFBenchInstruction38.0%27.7Artificial Analysis
EuroEval FrenchMultilingual24.3%32.7EuroEval
EuroEval DutchMultilingual24.1%32.5EuroEval
τ²-Bench Tool-Agent-User EvaluationAgentic20.8%13.8Victor Barres et al.
EuroEval PolishMultilingual20.2%27.5EuroEval
EuroEval PortugueseMultilingual19.5%26.7EuroEval
EuroEval SwedishMultilingual19.3%26.4EuroEval
EuroEval ItalianMultilingual16.6%23.1EuroEval
Artificial Analysis Long Context ReasoningReasoning16.3%19.6Artificial Analysis
EuroEval SpanishMultilingual14.6%20.6EuroEval
EuroEval GermanMultilingual12.9%18.5EuroEval
Artificial Analysis Intelligence IndexKnowledge7.8%32.1Artificial Analysis
Artificial Analysis Coding IndexCoding7.2%24.1Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge6.6%22.0Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge4.8%29.8Artificial Analysis
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial 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