GPT-5.1
Sharper GPT-5 generation for coding, product work, and tool-assisted tasks
Shogo Agent Index
Supported#57 of 9238.8range 30.4–47.3 · 36% of weight measured
Agentic coding
40
57% measured
Long-horizon autonomy
49
30% measured
Knowledge-work agents
32
20% measured
Computer use
29
estimated
Security & context learning
44
50% measured
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | 68.0% | 8% | source | |
| Terminal-Bench 2.0 | 47.6% | 8% | Terminus 2 | |
| DeepSWE | est. | 6% | predicted 38 | |
| FrontierSWE | est. | 5% | predicted 9 | |
| CursorBench | est. | 4% | predicted 33 | |
| GSO-Bench | 13.7% | 4% | OpenHands | |
| METR Time Horizons | est. | 10% | predicted 71 | |
| Vending-Bench 2 | $1,473 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 22 | |
| APEX-Agents | est. | 8% | predicted 36 | |
| GDPval | est. | 7% | predicted 40 | |
| Remote Labor Index | est. | 5% | predicted 2 | |
| DeepResearch Bench | 42.8% | 5% | source | |
| OSWorld 2.0 | est. | 6% | predicted 6 | |
| OSWorld | est. | 4% | predicted 65 | |
| Cybench | est. | 5% | predicted 64 | |
| CL-bench | 23.7% | 5% | source |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 72.8% | source |
| ARC-AGI-2 | Reasoning | 17.6% | source |
| Chess Puzzles | Reasoning | 42.0% | source |
| CritPt | Reasoning | 4.9% | source |
| DTBench | Knowledge | 90.1% | source |
| GPQA Diamond | Reasoning | 87.6% | source |
| Humanity's Last Exam | Reasoning | 23.7% | source |
| LMCA | Knowledge | 43.9% | source |
| OTIS Mock AIME | Math | 88.6% | source |
| SciCode | Coding | 43.3% | source |
| SimpleBench | Reasoning | 53.2% | source |
| SimpleQA Verified | Knowledge | 48.0% | source |
| VPCT | Multimodal | 58.7% | source |
| WebDev Arena | Coding | 1392 | source |