Google
availableShows if the model has enough results for an index.Gemma 3 27B
Gemma 3 27B is a non-reasoning model from Google. 18 benchmarks count toward its score, in 8 categories.
IndexOverall score out of 100.27.0 ±3.8
CoverageShare of the index weight with results.100%
SpeedOutput tokens per second.31/s
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.32K
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
18 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. |
|---|---|---|---|---|---|---|
| MATH level 5 | Math | 74.0% | 35.1 | — | — | Epoch AI |
| EuroEval Swedish | Multilingual | 58.4% | 75.1 | — | — | EuroEval |
| EuroEval Swedish | Multilingual | 58.0% | 74.8 | — | — | EuroEval |
| EuroEval French | Multilingual | 58.0% | 74.7 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 57.7% | 74.4 | — | — | EuroEval |
| EuroEval French | Multilingual | 57.5% | 74.1 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 56.5% | 72.9 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 55.7% | 71.8 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 53.8% | 69.4 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 53.5% | 69.1 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 51.8% | 67.0 | — | — | EuroEval |
| EuroEval German | Multilingual | 50.7% | 65.6 | — | — | EuroEval |
| EuroEval Spanish | Multilingual | 49.2% | 63.7 | — | — | EuroEval |
| Artificial Analysis MMMU-Pro | Multimodal | 48.0% | 25.8 | — | — | Artificial Analysis |
| GPQA diamond | Knowledge | 47.7% | 22.3 | — | — | Epoch AI |
| EuroEval German | Multilingual | 47.2% | 61.2 | — | — | EuroEval |
| EuroEval Spanish | Multilingual | 43.8% | 57.0 | — | — | EuroEval |
| Artificial Analysis GPQA Diamond | Knowledge | 42.8% | 12.4 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 31.8% | 21.4 | — | — | Artificial Analysis |
| Artificial Analysis SciCode | Coding | 23.3% | 25.2 | — | — | Artificial Analysis |
| OTIS Mock AIME 2024-2025 | Math | 22.5% | 24.2 | — | — | Epoch AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 13.0% | 30.0 | — | — | Artificial Analysis |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 10.5% | 6.4 | — | — | Victor Barres et al. |
| Artificial Analysis Coding Index | Coding | 10.1% | 26.1 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 7.3% | 13.3 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 4.8% | 28.5 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 4.4% | 29.3 | — | — | Artificial Analysis |
| Artificial Analysis Agentic Index | Agentic | 0.1% | 37.3 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 0.0% | 35.6 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
| Chess Puzzles | Reasoning | 0.0% | 23.5 | — | — | Epoch AI |
18 benchmarks count, from 31 of 31 results. A grey row does not count. Too few models took that benchmark.