Google
availableShows if the model has enough results for an index.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.
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 100Results
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 Professional | Knowledge | 69.4% | 29.8 | — | — | Yubo Wang et al. |
| Graduate-Level Google-Proof Q&A | Knowledge | 58.6% | 32.3 | — | — | David Rein et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 57.6% | 27.6 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 51.4% | 29.9 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 44.2% | 34.0 | — | — | Artificial Analysis |
| EuroEval Dutch | Multilingual | 33.2% | 43.8 | — | — | EuroEval |
| Artificial Analysis Long Context Reasoning | Reasoning | 32.0% | 30.4 | — | — | Artificial Analysis |
| EuroEval French | Multilingual | 30.1% | 39.9 | — | — | EuroEval |
| EuroEval Swedish | Multilingual | 29.2% | 38.8 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 27.6% | 36.8 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 26.4% | 35.2 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 25.2% | 33.8 | — | — | EuroEval |
| EuroEval Spanish | Multilingual | 23.6% | 31.8 | — | — | EuroEval |
| EuroEval German | Multilingual | 21.7% | 29.5 | — | — | EuroEval |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 20.8% | 13.8 | — | — | Victor Barres et al. |
| Artificial Analysis Coding Index | Coding | 9.4% | 25.6 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 8.9% | 33.5 | — | — | Artificial Analysis |
| Artificial Analysis Omniscience Accuracy | Knowledge | 8.6% | 24.5 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 3.8% | 28.7 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.6% | 39.6 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 0.0% | 35.6 | — | — | Artificial Analysis |
14 benchmarks count, from 21 of 21 results. A grey row does not count. Too few models took that benchmark.