GPT-5.4 vs GPT-5.4 Pro
Full profiles: GPT-5.4 (OpenAI) and GPT-5.4 Pro (OpenAI): every benchmark, price and rank.
Updated · Data from 12 sources
As of 10 Nov 2026, GPT-5.4 and GPT-5.4 Pro are neck and neck on quality (63.2 vs 63.3 on the BenchLeader Index, inside the ±4.6 margin), and GPT-5.4 is 12× cheaper at $5.63 vs $67.50 per 1M tokens blended. Choose GPT-5.4 for instruction following (72 vs 63), where it also streams 3×+ faster; choose GPT-5.4 Pro for fast first answers (9.2 s vs 111.7 s) and knowledge (74 vs 59), multimodal (70 vs 61), and reasoning (73 vs 66).
Key facts (as of 10 Nov 2026)
- GPT-5.4 scores 63.2 on the BenchLeader Index and GPT-5.4 Pro scores 63.3 (BenchLeader, 10 Nov 2026).
- GPT-5.4 costs $5.63 per 1M tokens blended (list price, 10 Nov 2026).
- GPT-5.4 Pro costs $67.50 per 1M tokens blended (list price, 10 Nov 2026).
- GPT-5.4 streams 3×+ faster than GPT-5.4 Pro (Artificial Analysis, 7-day median, 10 Nov 2026).
- Of the 1 benchmarks both models have, GPT-5.4 Pro leads 1 (BenchLeader, 10 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Reasoning | GPT-5.4 Pro | 73 vs 66 category score; Humanity's Last Exam 44.3% vs 36.2% | Medium |
| Knowledge | GPT-5.4 Pro | 74 vs 59 category score | High |
| Images and other media | GPT-5.4 Pro | 70 vs 61 category score | High |
| Following instructions | GPT-5.4 | 72 vs 63 category score | High |
| Lowest cost | GPT-5.4 | $5.63 vs $67.50 per 1M blended; agentic coding session $0.210 vs $2.52 | – |
| Fastest first answer | GPT-5.4 Pro | 9.2 s (GPT-5.4 Pro) vs 111.7 s (GPT-5.4 (xhigh)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GPT-5.4 (xhigh) and GPT-5.4 Pro are neck and neck on quality (63.2 vs 63.3, within the ±4.6 margin).
- GPT-5.4 (xhigh) is stronger in agents & tools, coding, instruction following, long context, maths.
- GPT-5.4 Pro is stronger in knowledge, multimodal, reasoning.
- GPT-5.4 (xhigh) is 12× cheaper ($5.63 vs $67.50 per 1M blended).
- GPT-5.4 (xhigh) streams 12.6× faster (76 vs 6 tokens per second).
At a glance
| Spec | GPT-5.4 | GPT-5.4 Pro |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | 5 Mar 2026 | 4 Mar 2026 |
| Context window (tokens) | 1,050,000 | 1,050,000 |
| Compared at | GPT-5.4 (xhigh) | GPT-5.4 Pro |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.50 / $15.00 / $0.250 | $30.00 / $180.00 / – |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | GPT-5.4 (xhigh) | GPT-5.4 Pro | Leader |
|---|---|---|---|
| Reasoning | 65.8 | 72.9 | GPT-5.4 Pro |
| Coding | 64.8 | – | not comparable |
| Agents & tools | 63.0 | – | not comparable |
| Maths | 65.1 | – | not comparable |
| Knowledge | 58.6 | 74.0 | GPT-5.4 Pro |
| Instruction following | 72.4 | 63.1 | GPT-5.4 |
| Multimodal | 60.9 | 69.8 | GPT-5.4 Pro |
| Long context | 65.7 | – | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Coding, Agents & tools, Maths, Long context, Human preference.
Where sources disagree
Across the 1 benchmarks both have, GPT-5.4 leads 0, GPT-5.4 Pro leads 1.
| Overall index | GPT-5.4 (xhigh) | GPT-5.4 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 63.2 | 63.3 | neck and neck |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | GPT-5.4 (xhigh) | GPT-5.4 Pro |
|---|---|---|
| Blended price per 1M tokens | $5.63 | $67.50 |
| Input / output per 1M | $2.50 / $15.00 | $30.00 / $180.00 |
| Cached input per 1M | $0.250 | – |
| Price per task: chat reply | $0.0055 | $0.066 |
| Price per task: summarize a 30-page report | $0.039 | $0.468 |
| Price per task: code edit | $0.037 | $0.450 |
| Price per task: agentic coding session | $0.210 | $2.52 |
| Price per task: structured extraction | $0.0080 | $0.096 |
| Agentic coding session, input mostly cached | $0.109 | – |
| Output speed | 76 tok/s | 6 tok/s |
| Time to first answer | 111.7 s | 9.2 s |
| Time to a complete answer | 195.8 s | – |
Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 (xhigh) scores 63.2 and takes 112 s to its first answer token; GPT-5.4 (low) scores 58.8 in 4 s, GPT-5.4 (high) scores 58.8 in 2 s. GPT-5.4 Pro scores 63.3 and takes 9 s to its first answer token; GPT-5.4 Pro (xhigh) scores 59.7 in 9 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
118 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | GPT-5.4 (xhigh) | GPT-5.4 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 63.2 | 63.3 |
| Agents & tools score | BenchLeader | 63.0 | – |
| Coding score | BenchLeader | 64.8 | – |
| Instruction following score | BenchLeader | 72.4 | 63.1 |
| Knowledge score | BenchLeader | 58.6 | 74.0 |
| Long context score | BenchLeader | 65.7 | – |
| Maths score | BenchLeader | 65.1 | – |
| Multimodal score | BenchLeader | 60.9 | 69.8 |
| Reasoning score | BenchLeader | 65.8 | 72.9 |
| Blended price $/M | BenchLeader | $5.63 | $67.50 |
| Output speed | BenchLeader | 76 tok/s | 6 tok/s |
| Time to first answer | BenchLeader | 111.7 s | 9.2 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 93.3% | 94.6%† |
| Humanity's Last Exam | Scale AI / CAIS | 36.2% | 44.3% |
| SimpleBench | SimpleBench | – | 74.1% |
| Arena Hard Prompts | Arena (LMArena) | 1487† | – |
| LiveBench 1.0 Reasoning | LiveBench | 88.1% | – |
| GPQA Diamond (AA) | Artificial Analysis | 92.0% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 43.7% | – |
| GPQA Diamond (Vals) | Vals AI | 91.7% | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 63.8%† | – |
| ARC-AGI-1 | ARC Prize | 93.7% | 94.5%† |
| ARC-AGI-2 | ARC Prize | 74.0% | 83.3%† |
| ARC-AGI-3 | ARC Prize | 0.2%† | – |
| CritPt | Artificial Analysis | 23.4% | 30.0%† |
| Chess Puzzles | Epoch AI Benchmarking Hub | 48.0% | 59.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 37.0% | – |
| CL-bench | Epoch AI Benchmarking Hub | 27.9% | – |
| CL-bench Life | Epoch AI Benchmarking Hub | 21.7% | – |
| LMCA | Epoch AI Benchmarking Hub | 52.0% | – |
| DTBench | Epoch AI Benchmarking Hub | 94.4% | – |
| ForecastBench | ForecastBench | 63.0%† | – |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 76.9%† | – |
| SciCode | SciCode | 56.6% | – |
| WeirdML | WeirdML | 77.7% | 57.4%† |
| GSO-Bench | GSO-Bench | 31.4% | – |
| Arena Coding | Arena (LMArena) | 1511† | – |
Show all 118 benchmarks
| Metric | Publisher | GPT-5.4 (xhigh) | GPT-5.4 Pro |
|---|---|---|---|
| Coding | |||
| Arena WebDev | Arena (LMArena) | 1400† | – |
| LiveBench 1.0 Coding | LiveBench | 77.5% | – |
| LiveCodeBench | Vals AI | 84.1% | – |
| SWE-bench (Vals) | Vals AI | 78.2% | – |
| SWE-Bench Pro | Scale AI SEAL | 59.1% | – |
| Code Migration | Vals AI | 35.0% | – |
| ProgramBench | Vals AI | 0.0% | – |
| Vibe Code Bench v1.1 | Vals AI | 67.4% | – |
| SWE-Bench Pro (private) | Scale AI SEAL | 59.1% | – |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 40.8% | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 44.3% | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 44.4% | – |
| MirrorCode | Epoch AI Benchmarking Hub | 15.6%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 51.8% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1607† | – |
| AlgoTune | AlgoTune | 1.9† | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 78.3% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 53.4† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 61.8 | – |
| Design Arena Website | Design Arena | 1194† | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 81.8%† | – |
| APEX-Agents | Mercor | 52.4%† | – |
| LiveBench Agentic Coding | LiveBench | 53.8% | – |
| Terminal-Bench Hard | Artificial Analysis | 57.6% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 87.1% | – |
| MCP Atlas | Scale AI SEAL | 70.6% | – |
| HiL-Bench | Scale AI SEAL | 9.7%† | – |
| τ³-bench Banking | τ²-bench | 39.4% | – |
| τ³-Banking (AA) | Artificial Analysis | 39.6% | – |
| APEX-Agents (AA) | Artificial Analysis | 33.3% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 0.0% | – |
| SkillsBench | Vals AI | 51.7% | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | 58.4%† | – |
| Arena Search | Arena (LMArena) | 1196† | – |
| DeepResearch Bench | DeepResearch Bench | 35.1%† | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 19.0%† | – |
| METR Time Horizons | METR | 74.3% | – |
| GBAEval | Epoch AI Benchmarking Hub | 45.1%† | – |
| Vending-Bench 2 | Andon Labs | 6144.2† | – |
| Design Arena Agentic | Design Arena | 1035† | – |
| DeepSearchQA | 63.7%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 78.6% | 82.5%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 49.0% | 58.5%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 95.3% | – |
| ProofBench | Vals AI | 56.0% | – |
| LiveBench Mathematics | LiveBench | 94.2% | – |
| AIME (Vals) | Vals AI | 96.7% | – |
| AIME 2026 | MathArena | 99.2% | – |
| HMMT February 2026 | MathArena | 97.7% | – |
| USAMO 2026 | MathArena | 95.2% | – |
| MathArena Apex | MathArena | 54.2% | 69.8%† |
| Arena Maths | Arena (LMArena) | 1459† | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 45.1% | 46.3%† |
| LiveBench 1.0 Data Analysis | LiveBench | 79.3% | – |
| MMLU-Pro | Vals AI | 87.5% | – |
| LegalBench | Vals AI | 86.0% | – |
| CorpFin | Vals AI | 65.3% | – |
| TaxEval | Vals AI | 74.0% | – |
| MedQA | Vals AI | 96.1% | – |
| PRBench Finance | Scale AI SEAL | 45.6%† | – |
| PRBench Legal | Scale AI SEAL | 44.4%† | – |
| MultiNRC | Scale AI SEAL | 58.3%† | 62.3% |
| CaseLaw v2 | Vals AI | 63.8% | – |
| MedCode | Vals AI | 41.3% | – |
| MedScribe | Vals AI | 77.5% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 25.4% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 82.6% | – |
| LiveBench Instruction Following | LiveBench | 70.2% | – |
| IFBench | Artificial Analysis | 74.0% | – |
| MultiChallenge | Scale AI SEAL | – | 69.2% |
| TutorBench | Scale AI SEAL | – | 56.6% |
| Arena Instruction Following | Arena (LMArena) | 1460† | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1465† | – |
| EQ-Bench 4 | EQ-Bench | 1258† | – |
| Arena Creative Writing | Arena (LMArena) | 1433† | – |
| Arena Multi-turn | Arena (LMArena) | 1480† | – |
| Arena Longer Queries | Arena (LMArena) | 1477† | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1292† | – |
| MMMU-Pro | Artificial Analysis | 78.4% | – |
| VISTA | Scale AI SEAL | 50.9%† | 53.9% |
| MMMU-Pro (Vals) | Vals AI | 87.5% | – |
| MortgageTax | Vals AI | 68.3% | – |
| VTB | Scale AI SEAL | 29.2%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 27.1%† | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.0% | – |
| Arena Document | Arena (LMArena) | 1471† | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 157.8† | 160.2 |
| LiveBench 1.0 | LiveBench | 78.0% | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 39.0 | – |
| AA Progress Index v1 | Artificial Analysis | 311.6 | – |
| Vals RSI Index | Vals AI | 15.5% | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 14.8% |
| MASK | Scale AI SEAL | 89.7%† | 91.7% |
Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
- GPT-5.4 (xhigh): 1 score revision.
- GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).
- GPT-5.4 Pro: BenchLeader Index 63.6 → 63.1.
- GPT-5.4 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).
- GPT-5.4 Pro: 1 score revision.
- GPT-5.4 (xhigh): 2 new results (USAMO 2026, τ³-bench Banking).
- GPT-5.4 (xhigh): 1 score revision.
- GPT-5.4 (xhigh): 1 new result (SWE Atlas: Codebase QnA).
- GPT-5.4 Pro: BenchLeader Index 62.1 → 63.6.
Related comparisons
- GPT-5.4 vs Claude Fable 5.2
- GPT-5.4 vs Claude Opus 5.5
- GPT-5.4 vs Gemini 4 Carbon
- GPT-5.4 Pro vs Claude Fable 5.2
- GPT-5.4 Pro vs Claude Opus 5.5
- GPT-5.4 Pro vs Gemini 4 Carbon
- GPT-5.4 Pro vs GPT-6 Astra
- GPT-5.3-Codex vs GPT-5.4 Pro
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GPT-5.4 vs GPT-5.4 Pro: questions
- Is GPT-5.4 better than GPT-5.4 Pro?
- GPT-5.4 (xhigh) and GPT-5.4 Pro are neck and neck on quality (63.2 vs 63.3, within the ±4.6 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 10 Nov 2026, so check the category scores for your use.
- GPT-5.4 vs GPT-5.4 Pro: which is cheaper, and will that change?
- GPT-5.4 is cheaper today: $5.63 against $67.50 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Which is faster, GPT-5.4 or GPT-5.4 Pro?
- GPT-5.4 streams 3×+ faster (76 vs 6 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Both accept 1,050,000 tokens of context.
- Which has lower latency?
- GPT-5.4 Pro answers first: 9.2 s against 111.7 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
More questions (2)
- Do independent benchmarks agree on GPT-5.4 vs GPT-5.4 Pro?
- Across the 1 benchmarks both have, GPT-5.4 leads 0, GPT-5.4 Pro leads 1.
- When was GPT-5.4 released?
- GPT-5.4 was released on 5 Mar 2026.