GPT-6.1 Sol
Near-Astra performance for complex coding, computer use, and professional work at a lower cost.
Shogo Agent Index
Estimated#5 of 9270.0range 62.2–77.7 · 18% of weight measured
Agentic coding
80
estimated
Long-horizon autonomy
78
50% measured
Knowledge-work agents
54
32% measured
Computer use
66
estimated
Security & context learning
62
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 89 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 96 | |
| DeepSWE | est. | 6% | predicted 82 | |
| FrontierSWE | est. | 5% | predicted 62 | |
| CursorBench | est. | 4% | predicted 56 | |
| GSO-Bench | est. | 4% | predicted 77 | |
| METR Time Horizons | est. | 10% | predicted 87 | |
| Vending-Bench 2 | $12,861 | 6% | source | |
| PostTrainBench | 38.8% | 4% | Codex CLI | |
| APEX-Agents | 60.0% | 8% | source | |
| GDPval | est. | 7% | predicted 71 | |
| Remote Labor Index | est. | 5% | predicted 21 | |
| DeepResearch Bench | est. | 5% | predicted 53 | |
| OSWorld 2.0 | est. | 6% | predicted 45 | |
| OSWorld | est. | 4% | predicted 96 | |
| Cybench | est. | 5% | predicted 94 | |
| CL-bench | est. | 5% | predicted 31 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 98.5% | source |
| ARC-AGI-2 | Reasoning | 94.2% | source |
| Chess Puzzles | Reasoning | 68.0% | source |
| CritPt | Reasoning | 31.7% | source |
| DTBench | Knowledge | 96.5% | source |
| FrontierCode | Coding | 50.2% | codex |
| FrontierMath Tiers 1-3 | Math | 93.7% | source |
| FrontierMath Tier 4 | Math | 100.0% | source |
| GPQA Diamond | Reasoning | 95.4% | source |
| LMCA | Knowledge | 62.8% | source |
| MirrorCode | Coding | 61.1% | source |
| OTIS Mock AIME | Math | 100.0% | source |
| ProofBench | Math | 99.0% | source |
| SciCode | Coding | 55.8% | source |
| SimpleBench | Reasoning | 82.9% | source |
| SimpleQA Verified | Knowledge | 73.9% | source |
| WebDev Arena | Coding | 1759 | source |
| WeirdML v3 | Coding | 38.3% | codex_cli |
API hosts
Live prices and uptime for every host serving GPT-6.1 Sol via OpenRouter.