GPT-4o (2024-08-06)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Shogo Agent Index
Supported#90 of 9212.2range 10–14.5 · 34% of weight measured
Agentic coding
10
34% measured
Long-horizon autonomy
22
50% measured
Knowledge-work agents
12
28% measured
Computer use
2
estimated
Security & context learning
11
50% measured
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | 31.0% | 8% | source | |
| Terminal-Bench 2.0 | est. | 8% | predicted 2 | |
| DeepSWE | est. | 6% | predicted 4 | |
| FrontierSWE | est. | 5% | predicted 0 | |
| CursorBench | est. | 4% | predicted 12 | |
| GSO-Bench | 0.0% | 4% | OpenHands | |
| METR Time Horizons | 40.8% | 10% | source | |
| Vending-Bench 2 | est. | 6% | predicted 0 | |
| PostTrainBench | est. | 4% | predicted 8 | |
| APEX-Agents | est. | 8% | predicted 5 | |
| GDPval | 9.9% | 7% | source | |
| Remote Labor Index | est. | 5% | predicted 0 | |
| DeepResearch Bench | est. | 5% | predicted 38 | |
| OSWorld 2.0 | est. | 6% | predicted 0 | |
| OSWorld | est. | 4% | predicted 6 | |
| Cybench | 12.5% | 5% | source | |
| CL-bench | est. | 5% | predicted 10 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 45.3% | source |
| ARC-AGI | Reasoning | 4.5% | source |
| ARC-AGI-2 | Reasoning | 0.0% | source |
| BALROG | Long-horizon | 32.3% | source |
| Chess Puzzles | Reasoning | 9.0% | source |
| CritPt | Reasoning | 0.0% | source |
| DTBench | Knowledge | 64.5% | source |
| Fiction.LiveBench | Long context | 66.7% | source |
| FrontierMath Tiers 1-3 | Math | 0.4% | source |
| GeoBench | Multimodal | 71.0% | source |
| GPQA Diamond | Reasoning | 49.2% | source |
| Humanity's Last Exam | Reasoning | 2.7% | source |
| LMCA | Knowledge | 16.6% | source |
| MATH Level 5 | Math | 53.3% | source |
| MMLU | Legacy | 88.1% | source |
| OTIS Mock AIME | Math | 6.4% | source |
| SimpleBench | Reasoning | 17.8% | source |
| SimpleQA Verified | Knowledge | 26.0% | source |
| TheAgentCompany | Knowledge work | 8.6% | source |
| VPCT | Multimodal | 40.0% | source |