Model
Qwen3 8B
Alibaba · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 0.0 | accuracy | N/A | Independent | low | epoch.ai |
| GeopoliticalQA | 2.5 | overall | N/A | Independent | medium | arxiv.org |
| GPQA Diamond | 56.8 | accuracy | N/A | Independent | high | epoch.ai |
| MS-Exam-Gen | 77.8 | accuracy | N/A | Independent | medium | arxiv.org |
| OTel | 60.4 | score | N/A | Independent | medium | arxiv.org |
| OUC-Benchmark | 64.5 | f1 | N/A | Independent | medium | arxiv.org |
| PHRBench | 66.5 | auroc | N/A | Independent | medium | arxiv.org |
Coding
CodingAgentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DrugTargetWorld | 4.6 | score | N/A | Independent | medium | arxiv.org |
| DyadMem | 47.4 | accuracy | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| VisualNoiseQA | 35.2 | accuracy | bp | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Intent-Eval | 91.7 | accuracy | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ObligationBench | 15.3 | recall | N/A | Independent | medium | arxiv.org |
| PFaithBench | 18.4 | overans | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DrillBench | 35.2 | accuracy | generative (bridge) | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…