ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.7 SonnetvsQwen3.6-Plus

Qwen3.6-Plus leads 2 of 3 shared benchmarks. Qwen3.6-Plus is 9.3x cheaper per token. Qwen3.6-Plus has the larger context window (1M tokens).

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

Shared benchmarks
1 – 2
Qwen3.6-Plus leads
Cheaper per token
Qwen3.6-Plus
9.3x cheaper, input + output
Larger context
Qwen3.6-Plus
1M tokens
Provider uptime (30d)
100% · —
Anthropic · Qwen
Claude 3.7 Sonnet
Anthropic · released 2025-02-24
textvision
Context
200K
Max out
128K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
5 · 5 core
Qwen3.6-Plus
Qwen · released 2026-04-02
textvision
Context
1M
Max out
Input /1M
$0.276
Output /1M
$1.65
Cached /1M
Scores
6 · 6 core
Quality

Benchmark matrix

BenchmarkClaude 3.7 SonnetQwen3.6-PlusΔEdge
Reported by both · 3
GPQA Diamond79.7% epoch88.4% epoch-8.7 ptQwen3.6-Plus
OTIS Mock AIME 2024-2025 (Epoch AI run)57.8% epoch93.3% epoch-35.5 ptQwen3.6-Plus
SWE-bench Verified (Epoch AI run)61% epoch57.9% epoch+3.1 ptClaude 3.7 Sonnet
Only Claude 3.7 Sonnet reports · 2
SWE-bench Verified70.3% not reported
AIME 202549.2% matharenanot reported
Only Qwen3.6-Plus reports · 3
LMArena Elonot reported1436.7
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported38.2% epoch
SimpleQA Verifiednot reported44.1% epoch
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 3.7 Sonnet minus Qwen3.6-Plus 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 3.7 SonnetQwen3.6-PlusEdge
Context window200K tokens1M tokensQwen3.6-Plus
Max output128K tokens
Input price / 1M$3 $0.276 Qwen3.6-Plus
Output price / 1M$15 $1.65 Qwen3.6-Plus
Cached input / 1M$0.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$1.93Qwen3.6-Plus
Modalitiestext · visiontext · visionTie
Released2025-02-242026-04-02
Cited benchmark scores56
Reliability

Provider status

All providers
More matchups

Claude 3.7 Sonnet vs …

More matchups

Qwen3.6-Plus vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.7 Sonnet and Qwen3.6-Plus on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.