Model
Qwen3.8 27B
Alibaba · open weights
Knowledge & Reasoning
Knowledge & ReasoningMath
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GraphDecide | 100.0 | accuracy | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CRUXEval-style | 39.4 | accuracy | N/A | Independent | medium | arxiv.org |
| SciCode | 46.6 | score | N/A | Independent | medium | artificialanalysis.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BioStudyBench | 56.0 | pass_rate | N/A | Independent | medium | arxiv.org |
| DUDA-Bench | 0.1 | workflow_score | react | Independent | medium | arxiv.org |
| DyadMem | 54.5 | accuracy | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| APM-Bench | 42.4 | overall_score | N/A | Independent | medium | arxiv.org |
| Ego-SpaCR | 22.3 | accuracy | native video | Independent | medium | arxiv.org |
| EMBER-Bench | 43.0 | accuracy | N/A | Independent | medium | arxiv.org |
| GeoSpatialBench | 52.5 | accuracy | N/A | Independent | medium | arxiv.org |
| InstanceBench | 63.5 | [email protected] | N/A | Independent | medium | arxiv.org |
| SpaceConflict | 56.6 | accuracy | N/A | Independent | medium | arxiv.org |
Long Context
Long Context| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| LongHarness Bench | 0.0 | accuracy | direct | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ObligationBench | 20.9 | recall | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…