GPT-6 Sol
OpenAI model for complex coding and agentic workflows
Shogo Agent Index
Estimated#13 of 9263.6range 54.2–73 · 14% of weight measured
Agentic coding
72
estimated
Long-horizon autonomy
76
30% measured
Knowledge-work agents
48
32% measured
Computer use
54
estimated
Security & context learning
59
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 86 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 92 | |
| DeepSWE | est. | 6% | predicted 72 | |
| FrontierSWE | est. | 5% | predicted 43 | |
| CursorBench | est. | 4% | predicted 49 | |
| GSO-Bench | est. | 4% | predicted 62 | |
| METR Time Horizons | est. | 10% | predicted 83 | |
| Vending-Bench 2 | $14,428 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 34 | |
| APEX-Agents | 54.3% | 8% | source | |
| GDPval | est. | 7% | predicted 64 | |
| Remote Labor Index | est. | 5% | predicted 12 | |
| DeepResearch Bench | est. | 5% | predicted 51 | |
| OSWorld 2.0 | est. | 6% | predicted 29 | |
| OSWorld | est. | 4% | predicted 92 | |
| Cybench | est. | 5% | predicted 90 | |
| CL-bench | est. | 5% | predicted 27 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 95.5% | source |
| ARC-AGI-2 | Reasoning | 89.6% | source |
| Chess Puzzles | Reasoning | 56.0% | source |
| CritPt | Reasoning | 30.9% | source |
| DTBench | Knowledge | 97.3% | source |
| FrontierCode | Coding | 49.3% | codex |
| FrontierMath Tiers 1-3 | Math | 89.8% | source |
| FrontierMath Tier 4 | Math | 90.0% | source |
| GPQA Diamond | Reasoning | 94.3% | source |
| LMCA | Knowledge | 59.1% | source |
| MirrorCode | Coding | 48.9% | source |
| OTIS Mock AIME | Math | 100.0% | source |
| ProofBench | Math | 83.0% | source |
| SciCode | Coding | 57.6% | source |
| SimpleBench | Reasoning | 73.1% | source |
| SimpleQA Verified | Knowledge | 60.7% | source |
| WebDev Arena | Coding | 1689 | source |
| WeirdML v3 | Coding | 19.7% | codex_cli |
API hosts
Live prices and uptime for every host serving GPT-6 Sol via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| OpenAI | $1.00 | $5.00 | $0.10 | $0.46 | 100.0% | — |
| Amazon Bedrock | $2.00 | $10.00 | $0.20 | $0.92 | 98.8% | — |
| Azure | $2.00 | $10.00 | $0.20 | $0.92 | 100.0% | — |
| OpenAI | $2.00 | $10.00 | $0.20 | $0.92 | 100.0% | — |
| OpenAI | $4.00 | $20.00 | $0.40 | $1.85 | 100.0% | — |