Claude 3 Opus
Claude 3 Opus from Anthropic.
Shogo Agent Index
Estimated#92 of 9211.0range 7.9–14.1 · 15% of weight measured
Agentic coding
11
estimated
Long-horizon autonomy
16
50% measured
Knowledge-work agents
12
estimated
Computer use
2
estimated
Security & context learning
10
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 | 29.5% | 10% | source | |
| 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 5 | |
| Cybench | 10.0% | 5% | source | |
| CL-bench | est. | 5% | predicted 9 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Chess Puzzles | Reasoning | 4.0% | source |
| DTBench | Knowledge | 61.6% | source |
| GPQA Diamond | Reasoning | 47.2% | source |
| LMCA | Knowledge | 17.0% | source |
| MATH Level 5 | Math | 37.5% | source |
| MMLU | Legacy | 84.6% | source |
| OTIS Mock AIME | Math | 4.7% | source |
| SimpleBench | Reasoning | 23.5% | source |
| SimpleQA Verified | Knowledge | 12.6% | source |