Gemini 1.5 Pro (Feb 2024)
Gemini 1.5 Pro (Feb 2024) from Google.
Shogo Agent Index
UnrankedNot ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
10
estimated
Long-horizon autonomy
20
estimated
Knowledge-work agents
12
estimated
Computer use
2
estimated
Security & context learning
8
50% measured
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 35 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 2 | |
| DeepSWE | est. | 6% | predicted 3 | |
| FrontierSWE | est. | 5% | predicted 0 | |
| CursorBench | est. | 4% | predicted 11 | |
| GSO-Bench | est. | 4% | predicted 0 | |
| METR Time Horizons | est. | 10% | predicted 37 | |
| Vending-Bench 2 | est. | 6% | predicted 0 | |
| PostTrainBench | est. | 4% | predicted 7 | |
| APEX-Agents | est. | 8% | predicted 5 | |
| GDPval | est. | 7% | predicted 9 | |
| Remote Labor Index | est. | 5% | predicted 0 | |
| DeepResearch Bench | est. | 5% | predicted 38 | |
| OSWorld 2.0 | est. | 6% | predicted 0 | |
| OSWorld | est. | 4% | predicted 4 | |
| Cybench | 7.5% | 5% | source | |
| CL-bench | est. | 5% | predicted 9 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI-2 | Reasoning | 0.8% | source |
| BALROG | Long-horizon | 21.0% | source |
| DTBench | Knowledge | 59.0% | source |
| GPQA Diamond | Reasoning | 57.2% | source |
| Humanity's Last Exam | Reasoning | 4.6% | source |
| MATH Level 5 | Math | 70.4% | source |
| MMLU | Legacy | 86.9% | source |
| OTIS Mock AIME | Math | 23.1% | source |
| SimpleBench | Reasoning | 27.1% | source |
| TheAgentCompany | Knowledge work | 3.4% | source |