GenMagic logoGenMagic
Sign in

Claude Sonnet 4.6 vs Qwen3.7 Max

Anthropic against Qwen. Prices, scores and speed below are live.

  • Qwen3.7 Max costs 63% less on blended price ($3.32 against $9.00 per 1M tokens, 3 input to 1 output).
  • Claude Sonnet 4.6 scores higher on the Artificial Analysis Intelligence Index: 30.5 against 29.9.
  • On the 29 benchmarks both have scores on, Claude Sonnet 4.6 leads on 15 and Qwen3.7 Max on 13, with 1 tied.
  • Both read up to 1M tokens of context.
  • Qwen3.7 Max is newer: listed May 21, 2026, against Feb 17, 2026.
Run both on your promptClaude Sonnet 4.6Qwen3.7 Max

Side by side

Claude Sonnet 4.6Qwen3.7 Max
LabAnthropicQwen
ListedFeb 17, 2026May 21, 2026
Input per 1M tokens$4.50$2.21
Output per 1M tokens$22.50$6.64
Cached input per 1M$0.45$0.44
Blended (3:1) per 1M$9.00$3.32
Context window1M1M
Max output128K131K
Knowledge cutoff--
Intelligence index30.529.9
Coding index6366
ReasoningYesYes
Reads imagesYesNo
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkClaude Sonnet 4.6Qwen3.7 Max
AIME71.1%Epoch AI95.6%Epoch AI
Artificial Analysis Agentic Index31.8Artificial Analysis and OpenRouter22.5Artificial Analysis and OpenRouter
Artificial Analysis Coding Index63Artificial Analysis and OpenRouter66Artificial Analysis and OpenRouter
Artificial Analysis Intelligence Index30.5Artificial Analysis and OpenRouter29.9Artificial Analysis and OpenRouter
Chess Puzzles23%Epoch AI26%Epoch AI
Design Arena: 3D1231 EloDesign Arena1263 EloDesign Arena
Design Arena: Android Native (agentic)1193 EloDesign Arena1155 EloDesign Arena
Design Arena: ASCII Art1233 EloDesign Arena1208 EloDesign Arena
Design Arena: Code1274 EloDesign Arena1274 EloDesign Arena
Design Arena: Data Viz1278 EloDesign Arena1276 EloDesign Arena
Design Arena: Full-stack (agentic)1213 EloDesign Arena1191 EloDesign Arena
Design Arena: Game Dev1259 EloDesign Arena1265 EloDesign Arena
Design Arena: Game Dev (agentic)1125 EloDesign Arena1107 EloDesign Arena
Design Arena: Godot Game Dev (agentic)1226 EloDesign Arena1187 EloDesign Arena
Design Arena: Mobile Apps (agentic)1212 EloDesign Arena1156 EloDesign Arena
Design Arena: SVG1193 EloDesign Arena1213 EloDesign Arena
Design Arena: UI Component1266 EloDesign Arena1264 EloDesign Arena
Design Arena: Web Apps (agentic)1175 EloDesign Arena1193 EloDesign Arena
Design Arena: Website1283 EloDesign Arena1274 EloDesign Arena
DTBench89.9%Epoch AI92.3%Epoch AI
GPQA Diamond69.3%Artificial Analysis and OpenRouter90.9%Artificial Analysis and OpenRouter
LMCA46.5Epoch AI44Epoch AI
Mystery Game Puzzles14%Epoch AI26%Epoch AI
ProofBench45%Epoch AI26%Epoch AI
SciCode46.8%Epoch AI49.5%Epoch AI
SimpleQA Verified32.8%Epoch AI55.8%Epoch AI
SWE-bench Verified75.2%Epoch AI77.3%Epoch AI
tau-bench (Airline)74.3%Artificial Analysis and OpenRouter72%Artificial Analysis and OpenRouter
WebDev Arena1521 EloEpoch AI1517 EloEpoch AI

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Anthropic models, Qwen models, every LLM's price and our sources.