Noometry

Model comparison

GPT-5.5 Instant vs gpt-oss-20b

GPT-5.5 Instant is the stronger model overall, scoring 42.5 to 32.1 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-5.5 Instant OpenAI

42.5

Rank #99 Confirmed

gpt-oss-20b OpenAI

32.1

Rank #249 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-5.5 Instant scores higher in 7 categories and gpt-oss-20b in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.5 Instant leads 62.0 to 35.8.
  • The biggest single-benchmark swing is GPQA Diamond: 82.5% for GPT-5.5 Instant and 60.8% for gpt-oss-20b.
  • gpt-oss-20b has downloadable open weights; the other is API-only.

Side by side

GPT-5.5 Instantgpt-oss-20b
ProviderOpenAIOpenAI
Noometry Index42.532.1
Released2026-05-052025-08-05
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.018
Output $ / M tokens—$0.09
Results tracked2734

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

Category by category

Coding GPT-5.5 Instant leads

GPT-5.5 Instant: 43.7 (#73), gpt-oss-20b: 37.1 (#185)

BenchmarkGPT-5.5 Instantgpt-oss-20b
SciCode48.6%34.4%
LMArena Coding14331307
WeirdML—40.9%
ALE-Bench—566.05

Agentic & Tool Use Not comparable

GPT-5.5 Instant: —, gpt-oss-20b: 9.2 (#146)

BenchmarkGPT-5.5 Instantgpt-oss-20b
Terminal-Bench—3.4%

Reasoning GPT-5.5 Instant leads

GPT-5.5 Instant: 24.2 (#149), gpt-oss-20b: 18.8 (#251)

BenchmarkGPT-5.5 Instantgpt-oss-20b
CritPt0%1.4%
Chess Puzzles12%4%
LMArena Hard Prompts14261274
Epoch Capabilities Index142.48137.81
Kagi LLM Benchmark—53.2%
DTBench—68%
LMCA—14.5%

Math gpt-oss-20b leads

GPT-5.5 Instant: 26.1 (#241), gpt-oss-20b: 37.6 (#93)

BenchmarkGPT-5.5 Instantgpt-oss-20b
OTIS Mock AIME 2024-202568.1%65.3%
LMArena Math14201317
FrontierMath (Tiers 1-3)26.3%—
FrontierMath Tier 42.4%—
Omni-MATH—56.5%

Knowledge GPT-5.5 Instant leads

GPT-5.5 Instant: 48.9 (#68), gpt-oss-20b: 34.6 (#186)

BenchmarkGPT-5.5 Instantgpt-oss-20b
GPQA Diamond82.5%60.8%
LMArena Expert14091258
MMLU-Pro—74%
GPQA (HELM)—59.4%

Multimodal Not comparable

GPT-5.5 Instant: 39.3 (#48), gpt-oss-20b: —

BenchmarkGPT-5.5 Instantgpt-oss-20b
LMArena Vision1250—
LMArena Document1403—

Multilingual GPT-5.5 Instant leads

GPT-5.5 Instant: 53.0 (#76), gpt-oss-20b: 42.4 (#192)

BenchmarkGPT-5.5 Instantgpt-oss-20b
LMArena Non-English14171269
LMArena Chinese14571311
LMArena German14101249
LMArena Japanese14081245
LMArena Korean13931239
LMArena Russian14301279
LMArena Spanish14301267
LMArena French1428—

Instruction Following GPT-5.5 Instant leads

GPT-5.5 Instant: 74.4 (#94), gpt-oss-20b: 62.0 (#235)

BenchmarkGPT-5.5 Instantgpt-oss-20b
LMArena Instruction Following14071236
IFEval—73.2%

Long Context GPT-5.5 Instant leads

GPT-5.5 Instant: 43.4 (#92), gpt-oss-20b: 37.9 (#203)

BenchmarkGPT-5.5 Instantgpt-oss-20b
LMArena Longer Query14221251

Writing & Preference GPT-5.5 Instant leads

GPT-5.5 Instant: 62.0 (#81), gpt-oss-20b: 35.8 (#260)

BenchmarkGPT-5.5 Instantgpt-oss-20b
LMArena Text14191288
LMArena Creative Writing14201201
LMArena Multi-Turn14341268
EQ-Bench Creative Writing—666
WildBench—73.7%

Frequently asked questions

Is GPT-5.5 Instant better than gpt-oss-20b?

GPT-5.5 Instant is the stronger model overall, scoring 42.5 to 32.1 on the Noometry Index.

Is GPT-5.5 Instant or gpt-oss-20b better for coding?

GPT-5.5 Instant scores higher on coding benchmarks: 43.7 versus 37.1 in the Noometry coding category.

How many benchmarks do GPT-5.5 Instant and gpt-oss-20b share?

22 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and gpt-oss-20b has 34.

Related comparisons

Go deeper