Model comparison
GPT-4.1 mini vs GPT-5.4
Head-to-head evidence from 19 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-4.1 mini #152 (Estimated); GPT-5.4 #8 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-4.1 mini and GPT-5.4 share 19 comparable benchmark results. 3 of 8 categories are comparable. 3 results are unique to GPT-4.1 mini; 33 to GPT-5.4.
Updated July 22, 2026- Shared results
- 19
- GPT-4.1 mini only
- 3
- GPT-5.4 only
- 33
- Comparable categories
- 3 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 7 evidence categories; 3 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 is clearly ahead on the BenchAlign aggregate, 74.24 to 44.19. 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 4.5. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 4.483% to 47.600%. GPT-4.1 mini does hit back in knowledge, 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 $0.40 input / $1.60 output per 1M tokens for GPT-4.1 mini. That is roughly 9.4x on output cost alone. GPT-5.4 is the reasoning model in the pair, while GPT-4.1 mini is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.4 gives you the larger context window at 1.05M, compared with 1M for GPT-4.1 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-4.1 mini | Δ | GPT-5.4 |
|---|---|---|---|
| Math | GPT-4.1 mini4.5 | Margin→ 38.0 | GPT-5.442.5 |
| Coding | GPT-4.1 mini23.6 | Margin→ 34.1 | GPT-5.457.7 |
| Knowledge | GPT-4.1 mini64.2 | Margin← 6.6 | GPT-5.457.6 |
| Agentic | GPT-4.1 miniNot measured | MarginNo overlap | GPT-5.477.2 |
| Multimodal | GPT-4.1 miniNot measured | MarginNo overlap | GPT-5.473.2 |
| Inst. Following | GPT-4.1 mini88.5 | MarginNo overlap | GPT-5.4Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 4.483%B 47.600%Winner: GPT-5.4Δ 43.1FrontierMath v2 (Tiers 1-3): GPT-4.1 mini scored 4.483%; GPT-5.4 scored 47.600%. GPT-5.4 wins this benchmark. - Source ↗
GPQA
KnowledgeA 64.2%B 92.8%Winner: GPT-5.4Δ 28.6GPQA: GPT-4.1 mini scored 64.2%; GPT-5.4 scored 92.8%. 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-4.1 mini | GPT-5.4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-4.1 mini$0.4 input / $1.6 output | GPT-5.4$2.5 input / $15 output | GPT-4.1 mini has the lower combined listed price. |
| Generation speedtokens per second | GPT-4.1 mini80 tok/s | GPT-5.474 tok/s | GPT-4.1 mini has the higher measured throughput. |
| First-answer latencyseconds to first token | GPT-4.1 mini0.76 s | GPT-5.4151.79 s | GPT-4.1 mini reaches the first token sooner. |
| Context windowmaximum listed tokens | GPT-4.1 mini1M | GPT-5.41.05M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | GPT-4.1 mini | GPT-5.4 | Result |
|---|---|---|---|
| AA Agentic IndexSource | 1.7% | 41.1% | GPT-5.4 leads |
| τ²-bench resultsSource | 52.9% | 87.1% | GPT-5.4 leads |
| GDPval-AASource | 0.1% | 44.7% | GPT-5.4 leads |
| GDPval-AASource | 503 | 1395 | GPT-5.4 leads |
| Terminal-Bench 2.0Source | — | 75.1% | Not comparable |
| CyberGymSource | — | 79.0% | Not comparable |
| BrowseCompSource | — | 82.7% | Not comparable |
| OSWorld-VerifiedSource | — | 75% | Not comparable |
| MCP AtlasSource | — | 70.6% | Not comparable |
| ToolathlonSource | — | 54.6% | Not comparable |
| Claw-EvalSource | — | 60.3% | Not comparable |
| DeepSearchQASource | — | 73.6% | Not comparable |
| APEX-Agents-AASource | — | 33.3% | Not comparable |
| Gert LabsSource | — | 64.89% | Not comparable |
| ResearchClawBenchSource | — | 15.3% | Not comparable |
| JobBenchSource | — | 38.9% | Not comparable |
| ExploitGymSource | — | 6.0% | Not comparable |
CodingGPT-5.4 wins7 benchmarks
| Benchmark | GPT-4.1 mini | GPT-5.4 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 23.6% | — | Not comparable |
| AA Coding IndexSource | 20.2% | 71.0% | GPT-5.4 leads |
| AA-SciCodeSource | 40.4% | 56.6% | GPT-5.4 leads |
| 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% | Not comparable |
Reasoning2 benchmarks
KnowledgeGPT-4.1 mini wins14 benchmarks
| Benchmark | GPT-4.1 mini | GPT-5.4 | Result |
|---|---|---|---|
| MMLUSource | 87.5% | — | Not comparable |
| GPQASource | 64.2% | 92.8% | GPT-5.4 leads |
| Artificial Analysis Intelligence IndexSource | 14.8% | 51.4% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 66.4% | 92.0% | GPT-5.4 leads |
| AA-HLESource | 4.6% | 41.6% | GPT-5.4 leads |
| AA-Omniscience IndexSource | -50.1% | 5.7% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 17.5% | 50.0% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 82.0% | 88.6% | GPT-4.1 mini leads |
| HLESource | — | 52.1% | Not comparable |
| HLE w/o toolsSource | — | 39.8% | Not comparable |
| GPQA-DSource | — | 92.8% | Not comparable |
| HealthBench HardSource | — | 40.1% | Not comparable |
| MedXpertQA (Text)Source | — | 59.6% | Not comparable |
| HealthBench ProfessionalSource | — | 48.1% | Not comparable |
MathGPT-5.4 wins2 benchmarks
Multimodal11 benchmarks
| Benchmark | GPT-4.1 mini | GPT-5.4 | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 58.7% | 78.4% | GPT-5.4 leads |
| Design Arena WebsiteSource | 1027 | 1250 | GPT-5.4 leads |
| MMMU-ProSource | — | 81.2% | Not comparable |
| OfficeQA ProSource | — | 53.2% | Not comparable |
| MMMU-Pro w/ PythonSource | — | 82.1% | Not comparable |
| 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 |
Frequently Asked Questions (4)
Which is better, GPT-4.1 mini or GPT-5.4?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 44.19. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 4.483% and 47.600%.
Which is better for knowledge tasks, GPT-4.1 mini or GPT-5.4?
GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 64.2 versus 57.6. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for coding, GPT-4.1 mini or GPT-5.4?
GPT-5.4 has the edge for coding in this comparison, averaging 57.7 versus 23.6. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Which is better for math, GPT-4.1 mini or GPT-5.4?
GPT-5.4 has the edge for math in this comparison, averaging 42.5 versus 4.5. Inside this category, FrontierMath v2 (Tiers 1-3) 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.