Model comparison
GPT-5.4 vs GPT-5.4 mini
Head-to-head evidence from 29 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Sibling matchup inside the GPT-5.4 family.
Public leaderboard positions: GPT-5.4 #8 (Supported); GPT-5.4 mini #75 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 and GPT-5.4 mini share 29 comparable benchmark results. 4 of 8 categories are comparable. 23 results are unique to GPT-5.4; 1 to GPT-5.4 mini.
Updated July 23, 2026- Shared results
- 29
- GPT-5.4 only
- 23
- GPT-5.4 mini only
- 1
- Comparable categories
- 4 / 8
GPT-5.4 makes more sense if mathematics is the priority or you need the larger 1.05M context window, while GPT-5.4 mini is the cleaner fit if multimodal & grounded is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 29 shared benchmark results across 7 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GPT-5.4 and GPT-5.4 mini sit in the same GPT-5.4 family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.
GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 56.77. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in mathematics, where it averages 42.5 against 21.7. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 27.100% to 2.080%. GPT-5.4 mini does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 output per 1M tokens, versus $0.75 input / $4.50 output per 1M tokens for GPT-5.4 mini. That is roughly 3.3x on output cost alone. GPT-5.4 gives you the larger context window at 1.05M, compared with 400K for GPT-5.4 mini.
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 | GPT-5.4 | Δ | GPT-5.4 mini |
|---|---|---|---|
| Math | GPT-5.442.5 | Margin← 20.8 | GPT-5.4 mini21.7 |
| Agentic | GPT-5.477.2 | Margin← 11.5 | GPT-5.4 mini65.7 |
| Knowledge | GPT-5.457.6 | Margin← 9.8 | GPT-5.4 mini47.8 |
| Multimodal | GPT-5.473.2 | Margin→ 3.4 | GPT-5.4 mini76.6 |
| Coding | GPT-5.457.7 | MarginNo overlap | GPT-5.4 miniNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tier 4)
MathA 27.100%B 2.080%Winner: GPT-5.4Δ 25FrontierMath v2 (Tier 4): GPT-5.4 scored 27.100%; GPT-5.4 mini scored 2.080%. GPT-5.4 wins this benchmark. - Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 47.600%B 28.280%Winner: GPT-5.4Δ 19.3FrontierMath v2 (Tiers 1-3): GPT-5.4 scored 47.600%; GPT-5.4 mini scored 28.280%. GPT-5.4 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 75.1%B 60%Winner: GPT-5.4Δ 15.1Terminal-Bench 2.0: GPT-5.4 scored 75.1%; GPT-5.4 mini scored 60%. GPT-5.4 wins this benchmark. - Source ↗
HLE
KnowledgeA 52.1%B 41.5%Winner: GPT-5.4Δ 10.6HLE: GPT-5.4 scored 52.1%; GPT-5.4 mini scored 41.5%. GPT-5.4 wins this benchmark. - Source ↗
GPQA
KnowledgeA 92.8%B 88%Winner: GPT-5.4Δ 4.8GPQA: GPT-5.4 scored 92.8%; GPT-5.4 mini scored 88%. GPT-5.4 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 | GPT-5.4 mini | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4$2.5 input / $15 output | GPT-5.4 mini$0.75 input / $4.5 output | GPT-5.4 mini has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.474 tok/s | GPT-5.4 mini201 tok/s | GPT-5.4 mini has the higher measured throughput. |
| First-answer latencyseconds to first token | GPT-5.4151.79 s | GPT-5.4 mini3.85 s | GPT-5.4 mini reaches the first token sooner. |
| Context windowmaximum listed tokens | GPT-5.41.05M | GPT-5.4 mini400K | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.4 wins17 benchmarks
| Benchmark | GPT-5.4 | GPT-5.4 mini | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 75.1% | 60% | GPT-5.4 leads |
| CyberGymSource | 79.0% | — | Not comparable |
| BrowseCompSource | 82.7% | — | Not comparable |
| OSWorld-VerifiedSource | 75% | 72.1% | GPT-5.4 leads |
| MCP AtlasSource | 70.6% | 57.7% | GPT-5.4 leads |
| ToolathlonSource | 54.6% | 42.9% | GPT-5.4 leads |
| τ²-bench resultsSource | 87.1% | 83.3% | GPT-5.4 leads |
| Claw-EvalSource | 60.3% | — | Not comparable |
| DeepSearchQASource | 73.6% | — | Not comparable |
| AA Agentic IndexSource | 41.1% | 30.2% | GPT-5.4 leads |
| APEX-Agents-AASource | 33.3% | 28.2% | GPT-5.4 leads |
| GDPval-AASource | 44.7% | 33.6% | GPT-5.4 leads |
| GDPval-AASource | 1395 | 1171 | GPT-5.4 leads |
| Gert LabsSource | 64.89% | — | Not comparable |
| ResearchClawBenchSource | 15.3% | — | Not comparable |
| JobBenchSource | 38.9% | — | Not comparable |
| ExploitGymSource | 6.0% | — | Not comparable |
Coding7 benchmarks
| Benchmark | GPT-5.4 | GPT-5.4 mini | Result |
|---|---|---|---|
| LiveCodeBench ProSource | 87.5% | — | Not comparable |
| SWE-bench ProSource | 57.7% | — | Not comparable |
| React Native EvalsSource | 85.3% | — | Not comparable |
| Vibe Code BenchSource | 67.42% | 47.97% | GPT-5.4 leads |
| AA Coding IndexSource | 71.0% | 56.1% | GPT-5.4 leads |
| AA-SciCodeSource | 56.6% | 49.9% | GPT-5.4 leads |
| FrontierCode 1.1 MainSource | — | 27.0% | Not comparable |
Reasoning2 benchmarks
KnowledgeGPT-5.4 wins13 benchmarks
| Benchmark | GPT-5.4 | GPT-5.4 mini | Result |
|---|---|---|---|
| GPQASource | 92.8% | 88% | GPT-5.4 leads |
| HLESource | 52.1% | 41.5% | GPT-5.4 leads |
| HLE w/o toolsSource | 39.8% | 28.2% | GPT-5.4 leads |
| GPQA-DSource | 92.8% | — | Not comparable |
| HealthBench HardSource | 40.1% | — | Not comparable |
| MedXpertQA (Text)Source | 59.6% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 51.4% | 40.0% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 92.0% | 87.5% | GPT-5.4 leads |
| AA-HLESource | 41.6% | 26.6% | GPT-5.4 leads |
| AA-Omniscience IndexSource | 5.7% | -18.7% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 50.0% | 37.5% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 88.6% | 89.8% | GPT-5.4 leads |
| HealthBench ProfessionalSource | 48.1% | — | Not comparable |
MathGPT-5.4 wins2 benchmarks
MultimodalGPT-5.4 mini wins11 benchmarks
| Benchmark | GPT-5.4 | GPT-5.4 mini | Result |
|---|---|---|---|
| MMMU-ProSource | 81.2% | 76.6% | GPT-5.4 leads |
| OfficeQA ProSource | 53.2% | — | Not comparable |
| MMMU-Pro w/ PythonSource | 82.1% | 78% | GPT-5.4 leads |
| CharXivSource | 82.8% | — | Not comparable |
| ERQASource | 65.4% | — | Not comparable |
| SimpleVQASource | 61.1% | — | Not comparable |
| ScreenSpot ProSource | 85.4% | — | Not comparable |
| ZeroBenchSource | 41.0% | — | Not comparable |
| MedXpertQA (MM)Source | 77.1% | — | Not comparable |
| AA-MMMU-ProSource | 78.4% | 73.3% | GPT-5.4 leads |
| Design Arena WebsiteSource | 1250 | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 | GPT-5.4 mini | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.9% | 73.3% | GPT-5.4 leads |
Frequently Asked Questions (5)
Which is better, GPT-5.4 or GPT-5.4 mini?
GPT-5.4 and GPT-5.4 mini are sibling variants in the GPT-5.4 family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard 74.24 to 56.77.
Which is better for knowledge tasks, GPT-5.4 or GPT-5.4 mini?
GPT-5.4 has the edge for knowledge tasks in this comparison, averaging 57.6 versus 47.8. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for math, GPT-5.4 or GPT-5.4 mini?
GPT-5.4 has the edge for math in this comparison, averaging 42.5 versus 21.7. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.4 or GPT-5.4 mini?
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77.2 versus 65.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.4 or GPT-5.4 mini?
GPT-5.4 mini has the edge for multimodal and grounded tasks in this comparison, averaging 76.6 versus 73.2. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
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.