GPT-6.1 Terra vs Qwen3.8 Max Preview
GPT-6.1 Terra leads Qwen3.8 Max Preview by 15.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6.1 Terra wins 9 and Qwen3.8 Max Preview wins 0 of 9 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-6.1 Terra | Qwen3.8 Max Preview |
|---|---|---|
| Agentic coding | 79 | 58 |
| Long-horizon autonomy | 74 | 63 |
| Knowledge-work agents | 56 | 46 |
| Computer use | 63 | 41 |
| Security & context learning | 62 | 52 |
Shared benchmarks
| Benchmark | GPT-6.1 Terra | Qwen3.8 Max Preview |
|---|---|---|
| APEX-Agentsindex | 68.3% | 63.3% |
| CritPt | 28.0% | 20.0% |
| FrontierMath Tier 4 | 92.7% | 46.3% |
| FrontierMath Tiers 1-3 | 90.9% | 74.7% |
| GPQA Diamond | 94.3% | 92.7% |
| MirrorCode | 76.7% | 52.2% |
| OTIS Mock AIME | 100.0% | 99.4% |
| SciCode | 55.1% | 53.2% |
| SimpleQA Verified | 57.3% | 45.8% |
Specs and price
| GPT-6.1 Terra | Qwen3.8 Max Preview | |
|---|---|---|
| Agent Index | 69 (#8) | 53.6 (#30) |
| Agent $/M | $0.42 | Free |
| Input / output $/M | $1.00 / $5.00 | Free / Free |
| Context | 1.1M | 1M |
| Released | Oct 26, 2026 | Jul 19, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 1 |
Don’t pick one. Route.
Shogo can run GPT-6.1 Terra and Qwen3.8 Max Preview side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo