SShogo Bench

Claude Haiku 5.5 vs Qwen3.8 Max Preview

Claude Haiku 5.5 leads Qwen3.8 Max Preview by 3.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 9 and Qwen3.8 Max Preview wins 4 of 14 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Qwen3.8 Max Preview
Agentic coding6758
Long-horizon autonomy6263
Knowledge-work agents4646
Computer use4741
Security & context learning5552

Shared benchmarks

BenchmarkClaude Haiku 5.5Qwen3.8 Max Preview
APEX-Agentsindex56.1%63.3%
FrontierSWEindex43.8%15.8%
Chess Puzzles55.0%46.0%
CritPt22.6%20.0%
DTBench95.0%92.0%
FrontierMath Tier 446.3%46.3%
FrontierMath Tiers 1-375.1%74.7%
GPQA Diamond89.6%92.7%
LMCA51.1%46.2%
MirrorCode78.9%52.2%
OTIS Mock AIME98.9%99.4%
ProofBench89.0%58.0%
SciCode55.0%53.2%
SimpleQA Verified23.8%45.8%

Specs and price

Claude Haiku 5.5Qwen3.8 Max Preview
Agent Index57.5 (#18)53.6 (#30)
Agent $/M$0.050Free
Input / output $/M$0.10 / $0.50Free / Free
Context1M1M
ReleasedOct 7, 2026Jul 19, 2026
WeightsClosedClosed
API hosts51

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 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