Noometry

Model comparison

gpt-oss-20b vs Qwen3.7 Flash

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 32.5 on the Noometry Index. gpt-oss-20b costs 1.5× less per token, which makes it the better buy when Qwen3.7 Flash's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

Qwen3.7 Flash Alibaba (Qwen)

39.9

Rank #156 Confirmed

Summary

  • They share 4 benchmarks with published results for both. gpt-oss-20b scores higher in 1 category and Qwen3.7 Flash in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.7 Flash leads 48.9 to 34.6.
  • The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 82.3% for Qwen3.7 Flash.
  • gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.03 / $0.13 for Qwen3.7 Flash.
  • Qwen3.7 Flash accepts more context: 1M tokens versus 131K.
  • gpt-oss-20b has downloadable open weights; the other is API-only.

Side by side

gpt-oss-20bQwen3.7 Flash
ProviderOpenAIAlibaba (Qwen)
Noometry Index32.539.9
Released2025-08-052026-07-15
WeightsOpenProprietary
Context window131K1M
Max output16K131K
Input $ / M tokens$0.018$0.03
Output $ / M tokens$0.09$0.13
Results tracked347

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

Category by category

Coding Not comparable

gpt-oss-20b: 37.6 (#192), Qwen3.7 Flash: —

Benchmarkgpt-oss-20bQwen3.7 Flash
SciCode34.4%—
WeirdML40.9%—
LMArena Coding1306—
ALE-Bench566.05—

Agentic & Tool Use Not comparable

gpt-oss-20b: 9.3 (#154), Qwen3.7 Flash: —

Benchmarkgpt-oss-20bQwen3.7 Flash
Terminal-Bench3.4%—

Reasoning Qwen3.7 Flash leads

gpt-oss-20b: 19.3 (#261), Qwen3.7 Flash: 28.2 (#108)

Benchmarkgpt-oss-20bQwen3.7 Flash
Chess Puzzles4%23%
Epoch Capabilities Index137.82144.64
Kagi LLM Benchmark53.2%—
NYT Connections (extended)—43.8%
CritPt1.4%—
LMArena Hard Prompts1274—
Mystery Game Puzzles—15%
DTBench68%—
LMCA14.5%—

Math gpt-oss-20b leads

gpt-oss-20b: 39.4 (#103), Qwen3.7 Flash: 38.3 (#140)

Benchmarkgpt-oss-20bQwen3.7 Flash
OTIS Mock AIME 2024-202565.3%86.7%
FrontierMath (Tiers 1-3)—19.3%
Omni-MATH56.5%—
LMArena Math1317—

Knowledge Qwen3.7 Flash leads

gpt-oss-20b: 34.6 (#195), Qwen3.7 Flash: 48.9 (#75)

Benchmarkgpt-oss-20bQwen3.7 Flash
GPQA Diamond60.8%82.3%
MMLU-Pro74%—
GPQA (HELM)59.4%—
LMArena Expert1258—

Multilingual Not comparable

gpt-oss-20b: 42.2 (#197), Qwen3.7 Flash: —

Benchmarkgpt-oss-20bQwen3.7 Flash
LMArena Non-English1268—
LMArena Chinese1314—
LMArena German1255—
LMArena Japanese1244—
LMArena Korean1236—
LMArena Russian1278—
LMArena Spanish1267—

Instruction Following Not comparable

gpt-oss-20b: 61.8 (#240), Qwen3.7 Flash: —

Benchmarkgpt-oss-20bQwen3.7 Flash
IFEval73.2%—
LMArena Instruction Following1236—

Long Context Not comparable

gpt-oss-20b: 37.9 (#209), Qwen3.7 Flash: —

Benchmarkgpt-oss-20bQwen3.7 Flash
LMArena Longer Query1250—

Writing & Preference Not comparable

gpt-oss-20b: 35.5 (#265), Qwen3.7 Flash: —

Benchmarkgpt-oss-20bQwen3.7 Flash
LMArena Text1287—
LMArena Creative Writing1201—
EQ-Bench Creative Writing666—
WildBench73.7%—
LMArena Multi-Turn1268—

Frequently asked questions

Is gpt-oss-20b better than Qwen3.7 Flash?

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 32.5 on the Noometry Index. gpt-oss-20b costs 1.5× less per token, which makes it the better buy when Qwen3.7 Flash's lead doesn't matter for your workload.

Which is cheaper, gpt-oss-20b or Qwen3.7 Flash?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen3.7 Flash lists at $0.03 and $0.13.

Which has the bigger context window?

Qwen3.7 Flash does, with 1M tokens against 131K.

How many benchmarks do gpt-oss-20b and Qwen3.7 Flash share?

4 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen3.7 Flash has 7.

Related comparisons

Go deeper