o4-mini
Fast o-series model for compact reasoning, coding, and tool use
Shogo Agent Index
Estimated#73 of 9229.8range 19.2–40.4 · 21% of weight measured
Agentic coding
31
11% measured
Long-horizon autonomy
39
50% measured
Knowledge-work agents
24
28% measured
Computer use
19
estimated
Security & context learning
32
estimated
Price
- Input
- $0.99/M
- Output
- $4.00/M
- Cache read
- $0.25/M
- 3:1 blend
- $1.74/M
- Agent-effective
- $0.53/M
Agent-effective = 20 input tokens per output token, 85% cache hits. Why.
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 66 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 34 | |
| DeepSWE | est. | 6% | predicted 24 | |
| FrontierSWE | est. | 5% | predicted 4 | |
| CursorBench | est. | 4% | predicted 26 | |
| GSO-Bench | 3.6% | 4% | OpenHands | |
| METR Time Horizons | 63.9% | 10% | source | |
| Vending-Bench 2 | est. | 6% | predicted 13 | |
| PostTrainBench | est. | 4% | predicted 17 | |
| APEX-Agents | est. | 8% | predicted 24 | |
| GDPval | 25.3% | 7% | source | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 45 | |
| OSWorld 2.0 | est. | 6% | predicted 2 | |
| OSWorld | est. | 4% | predicted 44 | |
| Cybench | est. | 5% | predicted 47 | |
| CL-bench | est. | 5% | predicted 17 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 72.0% | source |
| AlgoTune | Coding | 1.72× | source |
| ARC-AGI | Reasoning | 58.7% | source |
| ARC-AGI-2 | Reasoning | 6.1% | source |
| Chess Puzzles | Reasoning | 22.0% | source |
| CritPt | Reasoning | 0.6% | source |
| DTBench | Knowledge | 77.6% | source |
| Fiction.LiveBench | Long context | 77.8% | source |
| FrontierMath Tiers 1-3 | Math | 36.1% | source |
| FrontierMath Tier 4 | Math | 4.9% | source |
| GeoBench | Multimodal | 64.0% | source |
| GPQA Diamond | Reasoning | 79.6% | source |
| Humanity's Last Exam | Reasoning | 18.1% | source |
| LMCA | Knowledge | 26.5% | source |
| MATH Level 5 | Math | 97.8% | source |
| OTIS Mock AIME | Math | 81.7% | source |
| SimpleBench | Reasoning | 38.7% | source |
| SimpleQA Verified | Knowledge | 19.6% | source |
| VPCT | Multimodal | 57.5% | source |