Model
Gemini 2.5 Pro Exp 03-25
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Balrog | 43.3 | average_progress | N/A | Independent | medium | balrogai.com |
| EnigmaEval | 4.1 | accuracy | N/A | Independent | medium | labs.scale.com |
| GPQA Diamond | 83.8 | accuracy | N/A | Independent | high | epoch.ai |
| HLE | 18.2 | accuracy | N/A | Independent | low | epoch.ai |
| LiveBench | 82.3 | global_average | N/A | Independent | medium | livebench.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Aider Polyglot | 72.9 | percent_correct | N/A | Independent | medium | aider.chat |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GeoBench | 81.0 | acw_country_% | N/A | Independent | medium | geobench.org |
Reproduced by the community
Loading community runs…