How do Qwen3.7 Max and Qwen3.7 Plus compare on coding benchmarks?

The comparison table shows SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, DeepSWE, and coding agent index scores for both Qwen3.7 Max and Qwen3.7 Plus when publicly disclosed.

LLM Comparison

Qwen3.7 Max vs Qwen3.7 Plus: benchmark scores, pricing & comparison.

Q: Which is better: Qwen3.7 Max or Qwen3.7 Plus?

AskClash compares Qwen3.7 Max and Qwen3.7 Plus side by side across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, and context window so you can see which model wins on each benchmark.

Side-by-side Qwen3.7 Max vs Qwen3.7 Plus comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.

Open live leaderboard Qwen3.7 Max model page Qwen3.7 Plus model page

Rank #12 vs #21AskClash overall scores 70.7 vs 55.7.

Pricing $2.50/$7.50 vs $0.40/$1.60Input and output token prices per 1M tokens when published.

Proprietary vs ProprietaryAlibaba vs Alibaba.

Qwen3.7 Max vs Qwen3.7 Plus benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

Metric	Qwen3.7 Max	Qwen3.7 Plus
Overall Score	70.7	55.7
Leaderboard Rank	#12	#21
RWT	7.5	7.5
HLE	41.4	34.7
GPQA	92.4	90.3
IFEval	94.3	94.6
SWE-bench	80.4	77.7
SWE-Pro	—	57.6
Terminal-Bench	69.7	70.3
OSWorld	—	73.3
MCP Atlas	76.4	73.2
Finance Agent	48.4	38.2
CharXiv	—	85.9
MMMU-Pro	—	79.0
Tau2	94.7	93.0
MRCR	90.4	91.7
Input Price (per 1M tokens)	$2.50	$0.40
Output Price (per 1M tokens)	$7.50	$1.60
Context Window	1M	1M
Benchmarks Published	11	15

Qwen3.7 Max vs Qwen3.7 Plus head-to-head charts

Qwen3.7 Max leads 7 and Qwen3.7 Plus leads 3 of 11 shared benchmarks. Qwen3.7 Plus is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Qwen3.7 MaxQwen3.7 Plus

Overall

70.7Qwen3.7 Max

55.7Qwen3.7 Plus

RWT

7.5Qwen3.7 Max

7.5Qwen3.7 Plus

HLE

41.4Qwen3.7 Max

34.7Qwen3.7 Plus

GPQA

92.4Qwen3.7 Max

90.3Qwen3.7 Plus

IFEval

94.3Qwen3.7 Max

94.6Qwen3.7 Plus

SWE-bench

80.4Qwen3.7 Max

77.7Qwen3.7 Plus

Terminal-Bench

69.7Qwen3.7 Max

70.3Qwen3.7 Plus

MCP Atlas

76.4Qwen3.7 Max

73.2Qwen3.7 Plus

Finance Agent

48.4Qwen3.7 Max

38.2Qwen3.7 Plus

Tau2

94.7Qwen3.7 Max

93.0Qwen3.7 Plus

MRCR

90.4Qwen3.7 Max

91.7Qwen3.7 Plus

Qwen3.7 Max

Input$2.50

Output$7.50

Workload$4.00

Context1M

Qwen3.7 Plus

Input$0.40

Output$1.60

Workload$0.72

Context1M

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More Qwen3.7 Max and Qwen3.7 Plus comparisons

Explore how Qwen3.7 Max and Qwen3.7 Plus stack up against other top-ranked LLMs.

Claude Fable 5 vs Qwen3.7 Max Claude Fable 5 vs Qwen3.7 Plus GPT-5.6 Sol vs Qwen3.7 Max GPT-5.6 Sol vs Qwen3.7 Plus Kimi K3 vs Qwen3.7 Max Kimi K3 vs Qwen3.7 Plus Claude Opus 4.8 vs Qwen3.7 Max Claude Opus 4.8 vs Qwen3.7 Plus Grok 4.5 vs Qwen3.7 Max Grok 4.5 vs Qwen3.7 Plus

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

Token pricing

Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.

Coverage matters

Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.

This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.