Skip to main content

Model comparison

GPT-5 (medium) vs GPT-OSS 20B

Data verified

Head-to-head evidence from 12 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

55.15/100
Margin
12.4pts
← winning
42.74/100
0 category wins0 category wins

Public leaderboard positions: GPT-5 (medium) #84 (Supported); GPT-OSS 20B #159 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5 (medium) and GPT-OSS 20B share 12 comparable benchmark results. 0 of 8 categories are comparable. 2 results are unique to GPT-5 (medium); 6 to GPT-OSS 20B.

Updated July 20, 2026
Shared results
12
GPT-5 (medium) only
2
GPT-OSS 20B only
6
Comparable categories
0 / 8

Benchmark data for GPT-5 (medium) and GPT-OSS 20B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGPT-5 (medium)GPT-OSS 20BComparison
Input / output priceUSD per 1M tokensGPT-5 (medium)Not availableGPT-OSS 20B$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondGPT-5 (medium)83 tok/sGPT-OSS 20B313 tok/sGPT-OSS 20B has the higher measured throughput.
First-answer latencyseconds to first tokenGPT-5 (medium)36.28 sGPT-OSS 20B0.65 sGPT-OSS 20B reaches the first token sooner.
Context windowmaximum listed tokensGPT-5 (medium)128KGPT-OSS 20B128KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
τ²-bench resultsSource 86.5%60.2%GPT-5 (medium) leads
AA Agentic IndexSource 3.1%Not comparable
APEX-Agents-AASource 0.7%Not comparable
GDPval-AASource 3.0%Not comparable
GDPval-AASource 559Not comparable
Coding
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
AA-SciCodeSource 41.1%34.4%GPT-5 (medium) leads
React Native EvalsSource 71%Not comparable
AA Coding IndexSource 20.7%Not comparable
Reasoning
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
AA-LCRSource 72.8%30.7%GPT-5 (medium) leads
CritPtSource 0.0%1.4%GPT-OSS 20B leads
Knowledge
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
Artificial Analysis Intelligence IndexSource 33.7%14.9%GPT-5 (medium) leads
AA-GPQA DiamondSource 84.2%68.8%GPT-5 (medium) leads
AA-HLESource 23.5%9.8%GPT-5 (medium) leads
AA-Omniscience IndexSource -10.1%-63.9%GPT-5 (medium) leads
AA-Omniscience AccuracySource 38.9%15.5%GPT-5 (medium) leads
AA-Omniscience Hallucination RateSource 80.1%94.1%GPT-5 (medium) leads
Math
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
AA MATH-500Source 99.1%Not comparable
Multimodal
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
AA-MMMU-ProSource 74.3%Not comparable
Design Arena WebsiteSource 1217885GPT-5 (medium) leads
Inst. Following
BenchmarkGPT-5 (medium)GPT-OSS 20BResult
AA-IFBenchSource 70.6%65.1%GPT-5 (medium) leads
Frequently Asked Questions (3)

Can I compare GPT-5 (medium) and GPT-OSS 20B on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for GPT-5 (medium) and GPT-OSS 20B today?

GPT-5 (medium): Pricing unavailable GPT-OSS 20B: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.