Gemma 3 27B
Gemma / Google
50scores
48benchmarks
$0 / $0 per 1M tokenscost in/out
Metadata
Gemma Closed/API
Aliases: gemma-3-27b-it, gemma-3-27b-it:free, google-gemma-3-27b-it, google/gemma-3-27b-it, google/gemma-3-27b-it:free
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| Berkeley Function-Calling Leaderboard | Agentic | 69 | 29.47% | 2026-05-27 |
| Clembench Multimodal v1.6.5 | Agentic | 6 | 61.39 | 2026-05-06 |
| LLM-WikiRace | Agentic | 16 | 30 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 372 | 10.5% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 284 | 3.8% | 2026-05-11 |
| OpenUGI | Alignment | 1068 | 20.43 | 2026-05-06 |
| Natural2Code | Coding | 3 | 0.84 | 2026-05-06 |
| SciCode | Coding | 358 | 21.2% | 2026-05-11 |
| NeoEvalPlusN | Creative | 134 | 10 | 2026-05-06 |
| GSMA Open Telco Leaderboard | Domain | 45 | 50.43 | 2026-05-06 |
| kluster.ai LLM Hallucination Detection Leaderboard | Factuality | 6 | 97.91 | 2026-05-06 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 34 | 92.60 | 2026-05-06 |
| BenchLM | General Knowledge | 110 | 17 | 2026-05-06 |
| Global-MMLU-Lite | General Knowledge | 6 | 0.75 | 2026-05-06 |
| Arena-Hard | Generalization | 23 | 15.0% | 2026-05-27 |
| NeedleBench | Generalization | 2 | 80.38% | 2026-05-27 |
| HealthBench Hard | Healthcare | 2 | 0.59 | 2026-05-27 |
| HUMAINE | Human Preference | 19 | 3.57 | 2026-05-06 |
| Artificial Analysis Intelligence Index | Intelligence | 419 | 10.31 | 2026-05-11 |
| FACTS Grounding | Intelligence | 12 | 0.38 | 2026-05-06 |
| Humanity's Last Exam | Intelligence | 334 | 4.7% | 2026-05-11 |
| MathVision | Intelligence | 66 | 46 | 2026-05-06 |
| MMLU-Pro | Intelligence | 244 | 66.9% | 2026-05-11 |
| HindiGen v1 | Language | 24 | 50.32 | 2026-05-06 |
| Open Arabic LLM Leaderboard | Language | 20 | 71.40 | 2026-05-06 |
| PIQA | Language | 7 | 83.70 | 2026-05-06 |
| J1-ENVS | Legal | 4 | 55.73 | 2026-05-26 |
| AIME 2025 | Math | 209 | 20.7% | 2026-05-11 |
| HiddenMath | Mathematics | 2 | 0.60 | 2026-05-06 |
| OTIS Mock AIME 2024-2025 | Mathematics | 25 | 19.72 | 2026-05-06 |
| BRIDGE Medical Leaderboard | Medical | 20 | 49.45 | 2026-05-27 |
| BRIDGE Medical Leaderboard | Medical | 102 | 39.9 | 2026-05-27 |
| BRIDGE Medical Leaderboard | Medical | 140 | 37.55 | 2026-05-27 |
| MEDIC Benchmark | Medical | 66 | 59.16 average normalized public table score | 2026-05-27 |
| Medmarks | Medical | 51 | 0.4610358850116875 | 2026-05-27 |
| AfroBench-Lite | Multilingual | 12 | 51.01 | 2026-05-06 |
| LanguageBench | Multilingual | 20 | 0.50 | 2026-05-06 |
| ChartQA | Multimodal | 21 | 0.78 | 2026-05-06 |
| InfoVQA | Multimodal | 6 | 0.71 | 2026-05-06 |
| Artificial Analysis Openness Index | Openness | 51 | 50 | 2026-05-11 |
| BIG-Bench Extra Hard | Reasoning | 5 | 0.19 | 2026-05-06 |
| ECLeKTic | Reasoning | 2 | 0.17 | 2026-05-06 |
| GPQA Diamond | Reasoning | 378 | 42.8% | 2026-05-11 |
| CritPt | Science | 193 | 0% | 2026-05-11 |
| Defects4J | Software Engineering | 34 | 0.184 | 2026-05-27 |
| RepairBench | Software Engineering | 34 | 0.173 | 2026-05-27 |
| SWE-bench Pro | Software Engineering | 10 | 11.38 | 2026-05-06 |
| Structured Output Benchmark | Structured Output | 17 | 84.70 | 2026-05-06 |
| WMT24++ | Translation | 10 | 0.53 | 2026-05-06 |
| Lech Mazur Writing | Writing | 15 | 7.99 | 2026-05-06 |
No matching rows.