Noometry

Model comparison

GPT-5 Mini vs Qwen3.7 Max

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 41.8 on the Noometry Index. GPT-5 Mini costs 5.5× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Qwen3.7 Max Alibaba (Qwen)

51.5

Rank #42 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5 Mini scores higher in 1 category and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.7 Max leads 49.2 to 23.9.
  • The biggest single-benchmark swing is SimpleQA Verified: 21.6% for GPT-5 Mini and 55.8% for Qwen3.7 Max.
  • GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
  • Qwen3.7 Max accepts more context: 1M tokens versus 400K.

Side by side

GPT-5 MiniQwen3.7 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index41.851.5
Released2025-08-072026-05-19
WeightsProprietaryProprietary
Context window400K1M
Max output128K131K
Input $ / M tokens$0.25$2.50
Output $ / M tokens$2$7.50
Results tracked6033

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3.7 Max leads

GPT-5 Mini: 40.1 (#146), Qwen3.7 Max: 50.4 (#45)

BenchmarkGPT-5 MiniQwen3.7 Max
SWE-bench Verified64.7%77.3%
SciCode39.2%48.8%
LMArena Coding14061498
ALE-Bench799.771,189
SWE-bench Verified (bash only)59.8%—
LMArena WebDev—1515
SWE-bench Multilingual39.7%—
WeirdML52.7%—
AlgoTune1.38—

Agentic & Tool Use GPT-5 Mini leads

GPT-5 Mini: 31.1 (#70), Qwen3.7 Max: 22.1 (#135)

BenchmarkGPT-5 MiniQwen3.7 Max
Terminal-Bench34.8%—
Berkeley Function Calling Leaderboard55.5%—
GBAEval—0.4%
Vending-Bench 2-31.18—

Reasoning Qwen3.7 Max leads

GPT-5 Mini: 23.9 (#168), Qwen3.7 Max: 49.2 (#38)

BenchmarkGPT-5 MiniQwen3.7 Max
CritPt0%13.4%
Chess Puzzles30%19%
LMArena Hard Prompts13801483
Mystery Game Puzzles10%32%
DTBench80.5%92.3%
LMCA34.2%44%
Epoch Capabilities Index145.52153.68
ARC-AGI-24.4%—
SimpleBench—70.4%
Kagi LLM Benchmark70.3%—
NYT Connections (extended)—85.1%
ARC-AGI-154.3%—
EnigmaEval8.2%—
EBR-Bench—9.5%
ForecastBench61—

Math Qwen3.7 Max leads

GPT-5 Mini: 46.7 (#69), Qwen3.7 Max: 62.4 (#32)

BenchmarkGPT-5 MiniQwen3.7 Max
FrontierMath (Tiers 1-3)46.7%64.6%
FrontierMath Tier 412.2%34.1%
OTIS Mock AIME 2024-202586.7%95.6%
ProofBench9%26%
LMArena Math13781490
Omni-MATH72.2%—
MATH Level 597.8%—
FrontierMath (Feb 2025 set)27.2%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge Qwen3.7 Max leads

GPT-5 Mini: 45.6 (#86), Qwen3.7 Max: 61.6 (#28)

BenchmarkGPT-5 MiniQwen3.7 Max
GPQA Diamond75%90.9%
SimpleQA Verified21.6%55.8%
LMArena Expert13791488
Humanity's Last Exam19.4%—
MMLU-Pro83.5%—
Confabulations13.3%—
Vectara Hallucination Rate12.9%—
GPQA (HELM)75.6%—

Multimodal Not comparable

GPT-5 Mini: 35.6 (#85), Qwen3.7 Max: —

BenchmarkGPT-5 MiniQwen3.7 Max
LMArena Vision1202—
VPCT40.2%—

Multilingual Qwen3.7 Max leads

GPT-5 Mini: 48.9 (#137), Qwen3.7 Max: 56.9 (#15)

BenchmarkGPT-5 MiniQwen3.7 Max
LMArena Non-English13631474
LMArena Chinese13851530
LMArena Russian13621484
LMArena French1386—
LMArena German1366—
LMArena Japanese1341—
LMArena Korean1308—
LMArena Spanish1355—

Instruction Following Too close to call

GPT-5 Mini: 76.2 (#46), Qwen3.7 Max: 76.7 (#38)

BenchmarkGPT-5 MiniQwen3.7 Max
LMArena Instruction Following13571460
IFEval92.7%—

Long Context Qwen3.7 Max leads

GPT-5 Mini: 41.9 (#132), Qwen3.7 Max: 45.4 (#40)

BenchmarkGPT-5 MiniQwen3.7 Max
LMArena Longer Query13551482
Fiction.LiveBench69.4%—

Writing & Preference Qwen3.7 Max leads

GPT-5 Mini: 55.2 (#148), Qwen3.7 Max: 65.0 (#54)

BenchmarkGPT-5 MiniQwen3.7 Max
LMArena Text13731476
LMArena Creative Writing13251449
LMArena Multi-Turn13631481
Short-Story Creative Writing83.1%—
EQ-Bench Creative Writing1313—
WildBench85.5%—
EQ-Bench 4—1110

Frequently asked questions

Is GPT-5 Mini better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 41.8 on the Noometry Index. GPT-5 Mini costs 5.5× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

Which is cheaper, GPT-5 Mini or Qwen3.7 Max?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

Is GPT-5 Mini or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 400K.

How many benchmarks do GPT-5 Mini and Qwen3.7 Max share?

27 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen3.7 Max has 33.

Related comparisons

Go deeper