GPT-6.1 Sol vs Muse Wonder
GPT-6.1 Sol leads Muse Wonder by 9.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6.1 Sol wins 11 and Muse Wonder wins 2 of 13 shared benchmarks. GPT-6.1 Sol is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-6.1 Sol | Muse Wonder |
|---|---|---|
| Agentic coding | 80 | 68 |
| Long-horizon autonomy | 78 | 70 |
| Knowledge-work agents | 54 | 50 |
| Computer use | 66 | 50 |
| Security & context learning | 62 | 57 |
Shared benchmarks
| Benchmark | GPT-6.1 Sol | Muse Wonder |
|---|---|---|
| APEX-Agentsindex | 60.0% | 66.1% |
| Vending-Bench 2index | $12,861 | $9,432 |
| PostTrainBenchindex | 38.8% | 24.2% |
| CritPt | 31.7% | 28.3% |
| DTBench | 96.5% | 95.2% |
| FrontierMath Tier 4 | 100.0% | 70.7% |
| FrontierMath Tiers 1-3 | 93.7% | 82.1% |
| LMCA | 62.8% | 56.8% |
| MirrorCode | 61.1% | 45.6% |
| OTIS Mock AIME | 100.0% | 99.4% |
| ProofBench | 99.0% | 84.0% |
| SciCode | 55.8% | 60.3% |
| WeirdML v3 | 38.3% | 15.1% |
Specs and price
| GPT-6.1 Sol | Muse Wonder | |
|---|---|---|
| Agent Index | 70 (#5) | 60.9 (#15) |
| Agent $/M | $0.84 | $1.69 |
| Input / output $/M | $2.00 / $10.00 | $4.00 / $20.00 |
| Context | 1.1M | 1M |
| Released | Sep 29, 2026 | Oct 12, 2026 |
| Weights | Closed | Closed |
| API hosts | 6 | 2 |
Don’t pick one. Route.
Shogo can run GPT-6.1 Sol and Muse Wonder side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo