o3
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
Shogo Agent Index
Supported#67 of 9231.4range 22.5–40.2 · 43% of weight measured
Agentic coding
34
34% measured
Long-horizon autonomy
42
50% measured
Knowledge-work agents
27
48% measured
Computer use
11
40% measured
Security & context learning
35
50% measured
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | 62.3% | 8% | source | |
| Terminal-Bench 2.0 | est. | 8% | predicted 41 | |
| DeepSWE | est. | 6% | predicted 28 | |
| FrontierSWE | est. | 5% | predicted 5 | |
| CursorBench | est. | 4% | predicted 28 | |
| GSO-Bench | 8.8% | 4% | OpenHands | |
| METR Time Horizons | 65.4% | 10% | source | |
| Vending-Bench 2 | est. | 6% | predicted 17 | |
| PostTrainBench | est. | 4% | predicted 18 | |
| APEX-Agents | est. | 8% | predicted 28 | |
| GDPval | 30.8% | 7% | source | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | 45.2% | 5% | source | |
| OSWorld 2.0 | est. | 6% | predicted 3 | |
| OSWorld | 23.0% | 4% | o3 (100 steps) | |
| Cybench | est. | 5% | predicted 53 | |
| CL-bench | 17.8% | 5% | source |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 81.3% | source |
| ARC-AGI | Reasoning | 60.8% | source |
| ARC-AGI-2 | Reasoning | 6.5% | source |
| Chess Puzzles | Reasoning | 37.0% | source |
| CritPt | Reasoning | 1.1% | source |
| DTBench | Knowledge | 84.8% | source |
| Fiction.LiveBench | Long context | 88.9% | source |
| FrontierMath Tiers 1-3 | Math | 33.3% | source |
| GeoBench | Multimodal | 74.0% | source |
| GPQA Diamond | Reasoning | 81.8% | source |
| Humanity's Last Exam | Reasoning | 20.3% | source |
| LMCA | Knowledge | 39.7% | source |
| MATH Level 5 | Math | 97.8% | source |
| OTIS Mock AIME | Math | 84.4% | source |
| SimpleBench | Reasoning | 53.1% | source |
| SimpleQA Verified | Knowledge | 49.4% | source |
| VPCT | Multimodal | 52.0% | source |
API hosts
Live prices and uptime for every host serving o3 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| OpenAI | $2.00 | $8.00 | $0.50 | $1.07 | 100.0% | — |