ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Sonnet 4.5vsQwen3.8-Max

Qwen3.8-Max leads 5 of 5 shared benchmarks. Qwen3.8-Max is 2.7x cheaper per token. Qwen3.8-Max has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 5
Qwen3.8-Max leads
Cheaper per token
Qwen3.8-Max
2.7x cheaper, input + output
Larger context
Qwen3.8-Max
1M tokens
Provider uptime (30d)
100% · —
Anthropic · Qwen
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Context
200K
Max out
64K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
21 · 10 core
Qwen3.8-Max
Qwen · released 2026-08-02
textvision
Context
1M
Max out
131K
Input /1M
$1.65
Output /1M
$4.95
Cached /1M
Scores
9 · 7 core
Quality

Benchmark matrix

BenchmarkClaude Sonnet 4.5Qwen3.8-MaxΔEdge
Reported by both · 5
GPQA Diamond83.4% 92.6% -9.2 ptQwen3.8-Max
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epoch46.3% epoch-43.9 ptQwen3.8-Max
FrontierMath Tiers 1-3 v2 (Epoch AI run)23.9% epoch74.7% epoch-50.8 ptQwen3.8-Max
OTIS Mock AIME 2024-2025 (Epoch AI run)77.8% epoch99.4% epoch-21.6 ptQwen3.8-Max
SimpleQA Verified30.7% epoch45.8% epoch-15.1 ptQwen3.8-Max
Only Claude Sonnet 4.5 reports · 15
SWE-bench Verified77.2% not reported
AIME 202584.2% matharenanot reported
Humanity's Last Exam (no tools)17.7% not reported
ARC-AGI-2 (Verified)13.6% not reported
GDPval-AA1276 not reported
Humanity's Last Exam (with tools)33.6% not reported
MCP Atlas43.8% not reported
MMMLU89.5% not reported
MMMU-Pro (no tools)63.4% not reported
MMMU-Pro (with tools)68.9% not reported
OSWorld-Verified61.4% not reported
SWE-bench Verified (Epoch AI run)71.3% epochnot reported
Tau2-bench Retail86.2% not reported
Tau2-bench Telecom98% not reported
Terminal-Bench 2.051% not reported
Only Qwen3.8-Max reports · 3
LMArena Elonot reported1480.6
SWE-Bench Pronot reported67.7%
Terminal-Bench 2.1not reported86.6%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Sonnet 4.5 minus Qwen3.8-Max in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecClaude Sonnet 4.5Qwen3.8-MaxEdge
Context window200K tokens1M tokensQwen3.8-Max
Max output64K tokens131K tokensQwen3.8-Max
Input price / 1M$3 $1.65 Qwen3.8-Max
Output price / 1M$15 $4.95 Qwen3.8-Max
Cached input / 1M$0.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$6.6Qwen3.8-Max
Modalitiestext · visiontext · visionTie
Released2025-09-292026-08-02
Cited benchmark scores219
Reliability

Provider status

All providers
More matchups

Claude Sonnet 4.5 vs …

More matchups

Qwen3.8-Max vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Sonnet 4.5 and Qwen3.8-Max on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.