Google
partialShows if the model has enough results for an index.Gemma 3 12B
Gemma 3 12B is a model from Google. 4 benchmarks count toward its score, in 4 categories.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.45%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.N/A
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
4 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. |
|---|---|---|---|---|---|---|
| EuroEval French | Multilingual | 55.4% | 71.4 | — | — | EuroEval |
| EuroEval Swedish | Multilingual | 55.0% | 71.0 | — | — | EuroEval |
| EuroEval French | Multilingual | 54.5% | 70.4 | — | — | EuroEval |
| EuroEval Swedish | Multilingual | 53.8% | 69.4 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 53.4% | 68.9 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 52.6% | 68.0 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 52.4% | 67.8 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 49.7% | 64.4 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 49.3% | 63.8 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 49.2% | 63.7 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 47.7% | 61.9 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 46.8% | 60.8 | — | — | EuroEval |
| EuroEval German | Multilingual | 45.3% | 58.8 | — | — | EuroEval |
| EuroEval Spanish | Multilingual | 45.1% | 58.6 | — | — | EuroEval |
| EuroEval German | Multilingual | 42.9% | 55.9 | — | — | EuroEval |
| GPQA diamond | Knowledge | 39.5% | 14.7 | — | — | Epoch AI |
| EuroEval Spanish | Multilingual | 39.1% | 51.1 | — | — | EuroEval |
| OTIS Mock AIME 2024-2025 | Math | 16.7% | 21.0 | — | — | Epoch AI |
| Chess Puzzles | Reasoning | 0.0% | 23.5 | — | — | Epoch AI |
4 benchmarks count, from 19 of 19 results. A grey row does not count. Too few models took that benchmark.