Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.4 mini vs GPT-OSS 20B

Data verified

Head-to-head evidence from 16 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.77/100
Margin
14.0pts
← winning
42.74/100
0 category wins0 category wins

Public leaderboard positions: GPT-5.4 mini #75 (Estimated); GPT-OSS 20B #159 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.4 mini and GPT-OSS 20B share 16 comparable benchmark results. 0 of 8 categories are comparable. 14 results are unique to GPT-5.4 mini; 2 to GPT-OSS 20B.

Updated July 23, 2026
Shared results
16
GPT-5.4 mini only
14
GPT-OSS 20B only
2
Comparable categories
0 / 8

Benchmark data for GPT-5.4 mini and GPT-OSS 20B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 16 shared benchmark results across 5 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.

GPT-5.4 mini is priced at $0.75 input / $4.50 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for GPT-OSS 20B. GPT-5.4 mini has the larger context window at 400K, compared with 128K for GPT-OSS 20B.

Category breakdown

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

Category scores and score margins for GPT-5.4 mini and GPT-OSS 20B
CategoryGPT-5.4 miniΔGPT-OSS 20B
AgenticGPT-5.4 mini65.7MarginNo overlapGPT-OSS 20BNot measured
KnowledgeGPT-5.4 mini47.8MarginNo overlapGPT-OSS 20BNot measured
MathGPT-5.4 mini21.7MarginNo overlapGPT-OSS 20BNot measured
MultimodalGPT-5.4 mini76.6MarginNo overlapGPT-OSS 20BNot measured

Operational comparison

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

MetricGPT-5.4 miniGPT-OSS 20BComparison
Input / output priceUSD per 1M tokensGPT-5.4 mini$0.75 input / $4.5 outputGPT-OSS 20B$0 input / $0 outputGPT-OSS 20B has the lower combined listed price.
Generation speedtokens per secondGPT-5.4 mini201 tok/sGPT-OSS 20B313 tok/sGPT-OSS 20B has the higher measured throughput.
First-answer latencyseconds to first tokenGPT-5.4 mini3.85 sGPT-OSS 20B0.65 sGPT-OSS 20B reaches the first token sooner.
Context windowmaximum listed tokensGPT-5.4 mini400KGPT-OSS 20B128KGPT-5.4 mini lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
Terminal-Bench 2.0Source 60%—Not comparable
OSWorld-VerifiedSource 72.1%—Not comparable
MCP AtlasSource 57.7%—Not comparable
ToolathlonSource 42.9%—Not comparable
τ²-bench resultsSource 83.3%60.2%GPT-5.4 mini leads
AA Agentic IndexSource 30.2%3.1%GPT-5.4 mini leads
APEX-Agents-AASource 28.2%0.7%GPT-5.4 mini leads
GDPval-AASource 33.6%3.0%GPT-5.4 mini leads
GDPval-AASource 1171559GPT-5.4 mini leads
Coding
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
Vibe Code BenchSource 47.97%—Not comparable
AA Coding IndexSource 56.1%20.7%GPT-5.4 mini leads
AA-SciCodeSource 49.9%34.4%GPT-5.4 mini leads
FrontierCode 1.1 MainSource 27.0%—Not comparable
React Native EvalsSource —71%Not comparable
Reasoning
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
AA-LCRSource 69.3%30.7%GPT-5.4 mini leads
CritPtSource 10.0%1.4%GPT-5.4 mini leads
Knowledge
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
GPQASource 88%—Not comparable
HLESource 41.5%—Not comparable
HLE w/o toolsSource 28.2%—Not comparable
Artificial Analysis Intelligence IndexSource 40.0%14.9%GPT-5.4 mini leads
AA-GPQA DiamondSource 87.5%68.8%GPT-5.4 mini leads
AA-HLESource 26.6%9.8%GPT-5.4 mini leads
AA-Omniscience IndexSource -18.7%-63.9%GPT-5.4 mini leads
AA-Omniscience AccuracySource 37.5%15.5%GPT-5.4 mini leads
AA-Omniscience Hallucination RateSource 89.8%94.1%GPT-5.4 mini leads
Math
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
FrontierMath v2 (Tiers 1-3)Source 28.280%—Not comparable
FrontierMath v2 (Tier 4)Source 2.080%—Not comparable
Multimodal
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
MMMU-ProSource 76.6%—Not comparable
MMMU-Pro w/ PythonSource 78%—Not comparable
AA-MMMU-ProSource 73.3%—Not comparable
Design Arena WebsiteSource —882Not comparable
Inst. Following
BenchmarkGPT-5.4 miniGPT-OSS 20BResult
AA-IFBenchSource 73.3%65.1%GPT-5.4 mini leads
Frequently Asked Questions (3)

Can I compare GPT-5.4 mini 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-5.4 mini and GPT-OSS 20B today?

GPT-5.4 mini: $0.75 input / $4.50 output per 1M tokens 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

Explore More

OpenAI Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 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.