Model
Qwen3-32B
Alibaba · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 0.3 | accuracy | N/A | Independent | low | epoch.ai |
| GeopoliticalQA | 2.5 | overall | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 65.7 | accuracy | N/A | Independent | high | epoch.ai |
| OUC-Benchmark | 65.8 | f1 | N/A | Independent | medium | arxiv.org |
| PHRBench | 70.2 | auroc | N/A | Independent | medium | arxiv.org |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EfficientOpt | 75.0 | solver_time_ratio | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Aider Polyglot | 40.0 | percent_correct | N/A | Independent | medium | aider.chat |
| SciCode | 35.4 | score | N/A | Independent | medium | artificialanalysis.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| 2D-FET-Bench V2 | 1.3 | pass@1 | react-3/c0 | Independent | medium | arxiv.org |
| ReFract | 0.5 | success_rate | function calling | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| VisualNoiseQA | 36.2 | accuracy | bp | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| PFaithBench | 33.8 | overans | N/A | Independent | medium | arxiv.org |
| RAGStress | 100.0 | accuracy | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DrillBench | 48.5 | accuracy | likelihood + pmi | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…