Model
Gemini 3 Flash Preview
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Balrog | 48.1 | average_progress | N/A | Independent | medium | balrogai.com |
| GPQA Diamond | 89.4 | accuracy | N/A | Independent | high | epoch.ai |
| PARCEL | 97.0 | accuracy | N/A | Independent | medium | arxiv.org |
| SimpleQA Verified | 66.8 | accuracy | N/A | Independent | high | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GSO | 9.8 | score_opt@1 | OpenHands | Independent | medium | gso-bench.github.io |
| SWE-bench Verified | 75.4 | resolved_rate | N/A | Independent | high | epoch.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| cua-speedrun | 79.6 | success_rate | N/A | Independent | medium | arxiv.org |
| DeepResearch Bench | 49.8 | average_score | N/A | Independent | medium | evals.futuresearch.ai |
| OpenGameEval | 51.6 | pass_rate | N/A | Independent | medium | arxiv.org |
| Terminal-Bench | 64.3 | accuracy | Junie CLI | Independent | medium | tbench.ai |
| Terminal-Bench | 51.7 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
| Terminal-Bench | 51.0 | accuracy | Gemini CLI | Independent | medium | tbench.ai |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DataVista | 66.3 | accuracy | N/A | Independent | medium | arxiv.org |
| EgoTools-Bench | 64.5 | egotools-bench_overall | N/A | Independent | medium | arxiv.org |
| FigCodeBench | 76.8 | mmos | N/A | Independent | medium | arxiv.org |
| GDP.pdf | 10.0 | gdp.pdf_score | N/A | Independent | medium | surgehq.ai |
| GeoBench | 88.0 | acw_country_% | N/A | Independent | medium | epoch.ai |
| HeiCo-FOCUS | 46.2 | accuracy | N/A | Independent | medium | arxiv.org |
| SpaceCast-Bench | 56.7 | accuracy | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Mental Health Stigma Benchmark | 0.7 | f1 | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…