Model
Grok-4.6
xAI · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 19.7 | accuracy | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 94.0 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 49.3 | accuracy | N/A | Independent | high | epoch.ai |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Australian SOC Benchmark | 83.2 | t2_accuracy | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DeepSWE | 67.5 | pass@1 | mini-swe-agent | Independent | medium | deepswe.datacurve.ai |
| SciCode | 56.5 | score | N/A | Independent | medium | artificialanalysis.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CineRecon | 54.7 | score | grok build 1.0.41 | Independent | medium | arxiv.org |
| DrivingBench | 11.0 | progress | cursor | Independent | medium | arxiv.org |
| KlinikeBench | 21.9 | strict_pass@1 | N/A | Independent | medium | arxiv.org |
| Mine Odyssey | 17.2 | success_rate | N/A | Independent | medium | arxiv.org |
| PersonaCUABench | 13.8 | success_rate | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ChemArgus | 33.4 | full_problem | text only | Independent | medium | arxiv.org |
| GDP.pdf | 17.2 | gdp.pdf_score | N/A | Independent | medium | surgehq.ai |
| OmniVCBench | 50.3 | accuracy | N/A | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Design Creativity Bench | 43.4 | overall | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CWE-bench | 57.0 | pass@1 | opencode | Independent | medium | arxiv.org |
| FIGS | 24.5 | automated_judge_applying_a_10-rule_taxonomy_separating_sycophancy_from_calibrated_validation | N/A | Independent | medium | arxiv.org |
| From Triage to Impact | 82.8 | macro_f1 | N/A | Independent | medium | arxiv.org |
| ImpactBench | 70.5 | impactbench_pos._(%) | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…