Model
Qwen3.8 Max
Alibaba · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 20.0 | accuracy | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 92.7 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 45.8 | accuracy | N/A | Independent | high | epoch.ai |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| OpenProblemBench | 2.4 | mean_judged_solve_rate | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| AAArena | 2288.2 | elo | codex | Independent | medium | arxiv.org |
| DeepSWE | 57.5 | pass@1 | mini-swe-agent | Independent | medium | deepswe.datacurve.ai |
| SciCode | 52.9 | score | N/A | Independent | medium | artificialanalysis.ai |
| SimuVerity | 25.0 | score | claude code | Independent | medium | arxiv.org |
| TaoD2C-Bench | 61.8 | accuracy | N/A | Independent | medium | arxiv.org |
| WorldSolver | 22.7 | score | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Argo-Bench | 24.4 | score | N/A | Independent | medium | arxiv.org |
| AutoDataBench | 58.6 | performance_of_models_trained_on_optimized_data_vs_baseline_prediction_accuracy_comparison | N/A | Independent | medium | arxiv.org |
| BOTTLED | 0.4 | f1 | N/A | Independent | medium | arxiv.org |
| CASE longitudinal multimodal benchmark | 58.3 | overall_(%) | N/A | Independent | medium | arxiv.org |
| DUDA-Bench | 0.3 | workflow_score | react | Independent | medium | arxiv.org |
| EngiWorld | 25.8 | engiscore | N/A | Independent | medium | arxiv.org |
| Learn2Play Bench | 56.4 | max | opencode | Independent | medium | arxiv.org |
| StoreBench | 0.6 | composite | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CogEmo-Bench | 46.3 | m-f1 | N/A | Independent | medium | arxiv.org |
| EMBER-Bench | 26.6 | accuracy | N/A | Independent | medium | arxiv.org |
| GDP.pdf | 23.2 | gdp.pdf_score | N/A | Independent | medium | surgehq.ai |
| HSS | 33.0 | pass@1 | N/A | Independent | medium | arxiv.org |
| PlotGround-1k | 57.7 | accuracy | N/A | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Design Creativity Bench | 58.1 | overall | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DistressBench | 0.8 | score | N/A | Independent | medium | arxiv.org |
| DRYLAB-Bench | 0.4 | floor-included_brs_s2 | N/A | Independent | medium | arxiv.org |
| ObligationBench | 18.0 | recall | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…