Model
Gemma 2 9B IT
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BoolQ | 85.7 | score | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 27.5 | accuracy | N/A | Independent | high | epoch.ai |
| LiveBench | 28.7 | global_average | N/A | Independent | medium | livebench.ai |
| MMLU | 72.1 | exact_match | N/A | Independent | medium | crfm.stanford.edu |
| PIQA | 83.7 | score | N/A | Independent | medium | arxiv.org |
| The Pile | 0.7 | bits_per_byte | N/A | Independent | medium | arxiv.org |
Math
MathAgentic / Tool Use
Agentic / Tool UseInstruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CreativePreferences | 0.7 | auc | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & AlignmentReproduced by the community
Loading community runs…