Model
Phi-4
Microsoft · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Balrog | 11.6 | average_progress | N/A | Independent | medium | balrogai.com |
| GPQA Diamond | 56.1 | accuracy | N/A | Independent | high | epoch.ai |
| LiveBench | 41.6 | global_average | N/A | Independent | medium | livebench.ai |
| MMLU | 84.8 | exact_match | N/A | Self-reported | medium | arxiv.org |
Coding
CodingAgentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| FinSkillBench | 0.0 | score | N/A | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CreativePreferences | 0.7 | auc | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DrillBench | 47.4 | accuracy | likelihood + pmi | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…