GPT-5.3 Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
Shogo Agent Index
Supported#37 of 9248.4range 38.5–58.4 · 32% of weight measured
Agentic coding
53
46% measured
Long-horizon autonomy
62
80% measured
Knowledge-work agents
37
estimated
Computer use
35
estimated
Security & context learning
47
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | 74.8% | 8% | source | |
| Terminal-Bench 2.0 | 78.4% | 8% | SageAgent | |
| DeepSWE | est. | 6% | predicted 47 | |
| FrontierSWE | est. | 5% | predicted 15 | |
| CursorBench | est. | 4% | predicted 37 | |
| GSO-Bench | est. | 4% | predicted 27 | |
| METR Time Horizons | 74.5% | 10% | source | |
| Vending-Bench 2 | $5,940 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 25 | |
| APEX-Agents | est. | 8% | predicted 44 | |
| GDPval | est. | 7% | predicted 46 | |
| Remote Labor Index | est. | 5% | predicted 4 | |
| DeepResearch Bench | est. | 5% | predicted 48 | |
| OSWorld 2.0 | est. | 6% | predicted 9 | |
| OSWorld | est. | 4% | predicted 75 | |
| Cybench | est. | 5% | predicted 73 | |
| CL-bench | est. | 5% | predicted 21 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| CritPt | Reasoning | 16.9% | source |
| WebDev Arena | Coding | 1370 | source |