Model
Gemini 2.5 Pro
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Contradiction Benchmark for Review Evaluation | 93.1 | accuracy | N/A | Independent | medium | arxiv.org |
| CritPt | 2.0 | accuracy | N/A | Independent | low | epoch.ai |
| GDPval | 23.3 | win_rate | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 85.3 | accuracy | N/A | Independent | high | epoch.ai |
| News QA | 68.8 | exact_match | N/A | Independent | medium | arxiv.org |
| PHRBench | 87.9 | auroc | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ARCS | 30.9 | ex_e2e | N/A | Independent | medium | arxiv.org |
| GSO | 3.9 | score_opt@1 | OpenHands | Independent | medium | gso-bench.github.io |
| SciCode | 42.8 | score | N/A | Independent | medium | artificialanalysis.ai |
| SWE-bench Verified | 57.6 | resolved_rate | N/A | Independent | high | epoch.ai |
| Web-Bench | 15.7 | pass@1 | N/A | Independent | medium | arxiv.org |
| WebUIProof | 42.9 | success_rate | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DeepResearch Bench | 41.5 | average_score | N/A | Independent | medium | evals.futuresearch.ai |
| FinSkillBench | 0.5 | score | N/A | Independent | medium | arxiv.org |
| GeoNatureAgent (GNA) | 48.0 | accuracy | N/A | Independent | medium | arxiv.org |
| Terminal-Bench | 32.6 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
| Terminal-Bench | 26.1 | accuracy | Mini-SWE-Agent | Independent | medium | tbench.ai |
| Terminal-Bench | 19.6 | accuracy | Gemini CLI | Independent | medium | tbench.ai |
| Terminal-Bench | 16.4 | accuracy | OpenHands | Independent | medium | tbench.ai |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BrainTRACE | 36.5 | accuracy | N/A | Independent | medium | arxiv.org |
| EgoGears | 53.7 | accuracy | N/A | Independent | medium | arxiv.org |
| ELMABench | 0.9 | bert | N/A | Independent | medium | arxiv.org |
| FG-Sudoku | 0.9 | accuracy | N/A | Independent | medium | arxiv.org |
| Front2Back-ReID | 60.6 | accuracy | N/A | Independent | medium | arxiv.org |
| RateAR | 0.8 | srcc | N/A | Independent | medium | arxiv.org |
| SpatialViz-Bench | 44.7 | overall_score | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningMultilingual
MultilingualReproduced by the community
Loading community runs…