Model
Gemini-3.5-flash
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 13.1 | accuracy | N/A | Independent | low | epoch.ai |
| EnigmaEval | 25.4 | accuracy | N/A | Independent | medium | labs.scale.com |
| GPQA Diamond | 92.8 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 66.2 | accuracy | N/A | Independent | high | epoch.ai |
| WorldFact-Bench | 32.2 | accuracy | direct judgment | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DeepSWE | 37.4 | pass@1 | mini-swe-agent | Independent | medium | deepswe.datacurve.ai |
| MathVis | 16.0 | pass@1 | N/A | Independent | medium | arxiv.org |
| SciCode | 53.1 | score | N/A | Independent | medium | artificialanalysis.ai |
| SWE-bench Verified | 79.3 | resolved_rate | N/A | Independent | high | epoch.ai |
| TaoD2C-Bench | 62.1 | accuracy | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CASE longitudinal multimodal benchmark | 56.3 | overall_(%) | N/A | Independent | medium | arxiv.org |
| DataSense-Bench | 35.1 | accuracy | N/A | Independent | medium | arxiv.org |
| IGMBench | 57.3 | success_rate | N/A | Independent | medium | arxiv.org |
| KlinikeBench | 15.6 | strict_pass@1 | N/A | Independent | medium | arxiv.org |
| Legal Research Bench | 30.8 | accuracy | N/A | Independent | medium | arxiv.org |
| OpenGameEval | 50.6 | pass_rate | N/A | Independent | medium | arxiv.org |
| UserProxyBench | 0.8 | ufs | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ChartBmkAgent | 80.3 | accuracy | N/A | Independent | medium | arxiv.org |
| EviLens | 61.8 | accuracy | N/A | Independent | medium | arxiv.org |
| FastBench | 50.7 | accuracy | N/A | Independent | medium | arxiv.org |
| GDP.pdf | 14.0 | gdp.pdf_score | N/A | Independent | medium | surgehq.ai |
| HSS | 32.6 | pass@1 | N/A | Independent | medium | arxiv.org |
| RateAR | 0.7 | srcc | N/A | Independent | medium | arxiv.org |
| SpaceCast-Bench | 58.0 | accuracy | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| SWE-DeceptionBench | 90.8 | active_deception_rate | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningMultilingual
MultilingualReproduced by the community
Loading community runs…