SShogo Bench

GPT-5.6 Terra vs Qwen3.8 Max Preview

GPT-5.6 Terra leads Qwen3.8 Max Preview by 5.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.6 Terra wins 11 and Qwen3.8 Max Preview wins 4 of 15 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.6 TerraQwen3.8 Max Preview
Agentic coding6658
Long-horizon autonomy6963
Knowledge-work agents4746
Computer use4841
Security & context learning5652

Shared benchmarks

BenchmarkGPT-5.6 TerraQwen3.8 Max Preview
APEX-Agentsindex58.2%63.3%
DeepSWEindex69.6%57.5%
Chess Puzzles47.0%46.0%
CritPt30.0%20.0%
DTBench93.3%92.0%
FrontierMath Tier 470.7%46.3%
FrontierMath Tiers 1-386.0%74.7%
GPQA Diamond93.3%92.7%
LMCA54.9%46.2%
MirrorCode41.1%52.2%
OTIS Mock AIME99.7%99.4%
ProofBench74.0%58.0%
SciCode55.0%53.2%
SimpleQA Verified43.2%45.8%
WebDev Arena15211671

Specs and price

GPT-5.6 TerraQwen3.8 Max Preview
Agent Index58.8 (#16)53.6 (#30)
Agent $/M$1.02Free
Input / output $/M$2.00 / $12.00Free / Free
Context1.1M1M
ReleasedJul 9, 2026Jul 19, 2026
WeightsClosedClosed
API hosts41

Don’t pick one. Route.

Shogo can run GPT-5.6 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