GPT-6 Luna
OpenAI's most efficient model for focused, high-volume tasks
Shogo Agent Index
UnrankedNot ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
56
estimated
Long-horizon autonomy
60
estimated
Knowledge-work agents
39
32% measured
Computer use
39
estimated
Security & context learning
50
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 79 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 77 | |
| DeepSWE | est. | 6% | predicted 53 | |
| FrontierSWE | est. | 5% | predicted 19 | |
| CursorBench | est. | 4% | predicted 39 | |
| GSO-Bench | est. | 4% | predicted 34 | |
| METR Time Horizons | est. | 10% | predicted 77 | |
| Vending-Bench 2 | est. | 6% | predicted 55 | |
| PostTrainBench | est. | 4% | predicted 26 | |
| APEX-Agents | 44.3% | 8% | source | |
| GDPval | est. | 7% | predicted 50 | |
| Remote Labor Index | est. | 5% | predicted 5 | |
| DeepResearch Bench | est. | 5% | predicted 49 | |
| OSWorld 2.0 | est. | 6% | predicted 12 | |
| OSWorld | est. | 4% | predicted 80 | |
| Cybench | est. | 5% | predicted 78 | |
| CL-bench | est. | 5% | predicted 23 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 86.7% | source |
| ARC-AGI-2 | Reasoning | 59.3% | source |
| Chess Puzzles | Reasoning | 36.0% | source |
| CritPt | Reasoning | 19.4% | source |
| DTBench | Knowledge | 90.1% | source |
| FrontierCode | Coding | 42.4% | codex |
| FrontierMath Tiers 1-3 | Math | 78.9% | source |
| FrontierMath Tier 4 | Math | 56.1% | source |
| GPQA Diamond | Reasoning | 90.5% | source |
| LMCA | Knowledge | 44.5% | source |
| MirrorCode | Coding | 26.7% | source |
| OTIS Mock AIME | Math | 98.9% | source |
| ProofBench | Math | 64.0% | source |
| SciCode | Coding | 54.6% | source |
| SimpleQA Verified | Knowledge | 41.4% | source |
| WebDev Arena | Coding | 1582 | source |
| WeirdML v3 | Coding | 7.9% | codex_cli |
API hosts
Live prices and uptime for every host serving GPT-6 Luna via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| OpenAI | $0.050 | $0.25 | $0.005 | $0.020 | 100.0% | — |
| Amazon Bedrock | $0.10 | $0.50 | $0.010 | $0.050 | 100.0% | — |
| Azure | $0.10 | $0.50 | $0.010 | $0.050 | 90.8% | — |
| OpenAI | $0.10 | $0.50 | $0.010 | $0.050 | 97.6% | — |
| OpenAI | $0.20 | $1.00 | $0.020 | $0.090 | 100.0% | — |