SShogo Bench

Claude Fable 5.2 vs Qwen3.8 Max Preview

Claude Fable 5.2 leads Qwen3.8 Max Preview by 22.8 points on the Shogo Agent Index. Claude Fable 5.2 wins 13 and Qwen3.8 Max Preview wins 0 of 13 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Qwen3.8 Max Preview
Agentic coding8658
Long-horizon autonomy7863
Knowledge-work agents6746
Computer use7741
Security & context learning6552

Shared benchmarks

BenchmarkClaude Fable 5.2Qwen3.8 Max Preview
APEX-Agentsindex80.1%63.3%
FrontierSWEindex69.9%15.8%
Chess Puzzles79.0%46.0%
CritPt35.7%20.0%
DTBench99.2%92.0%
FrontierMath Tier 4100.0%46.3%
FrontierMath Tiers 1-395.1%74.7%
GPQA Diamond96.0%92.7%
LMCA70.6%46.2%
OTIS Mock AIME99.7%99.4%
ProofBench100.0%58.0%
SciCode67.7%53.2%
SimpleQA Verified94.0%45.8%

Specs and price

Claude Fable 5.2Qwen3.8 Max Preview
Agent Index76.4 (#1)53.6 (#30)
Agent $/M$3.21Free
Input / output $/M$8.00 / $40.00Free / Free
Context1M1M
ReleasedNov 9, 2026Jul 19, 2026
WeightsClosedClosed
API hosts41

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 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