Model
Qwen2.5 14B Instruct
Alibaba · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| MMLU | 79.9 | exact_match | N/A | Independent | medium | arxiv.org |
| ViLegalExpert | 70.1 | score | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| WebUIProof | 26.1 | success_rate | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| JointCoreBench | 0.5 | minimum-cost_recovery | N/A | Independent | medium | arxiv.org |
Multimodal
MultimodalInstruction 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…