GPT-5 vs GPT-5.4
GPT-5 Verdict
- GPT-5.4 leads on quality: 63.5 vs 60.8.
- GPT-5 is stronger in coding, maths, reasoning.
- GPT-5.4 is stronger in agents & tools, composite, human preference, instruction following, knowledge, long context, multimodal.
- GPT-5 is 1.6× cheaper ($3.44 vs $5.63 per 1M blended).
- GPT-5.4 streams 1.6× faster (132 vs 85 tokens per second).
| Metric | GPT-5 | GPT-5.4 |
|---|---|---|
| BenchLeader Index | 60.8 | 63.5 |
| Agents & tools score | 51.0 | 66.2 |
| Coding score | 60.9 | 51.6 |
| Composite score | 58.1 | 78.4 |
| Human preference score | 61.7 | 64.7 |
| Instruction following score | 65.0 | 71.9 |
| Knowledge score | 62.2 | 67.0 |
| Long context score | 65.6 | 67.6 |
| Maths score | 72.8 | – |
| Multimodal score | 59.6 | 64.0 |
| Reasoning score | 64.2 | 62.6 |
| Blended price $/M | $3.44 | $5.63 |
| Output speed | 85 tok/s | 132 tok/s |
| Time to first answer | 60.7 s | 102.0 s |
| Context window | 400k | 1.1M |
| Terminal-Bench | 49.6% | 81.8% |
| SciCode | 42.9% | – |
| Remote Labor Index | 1.7% | – |
| WeirdML | 39.8% | – |
| APEX-Agents | 18.3% | 34.9% |
| Epoch Capabilities Index | 150 | 156.9 |
| LMArena Text | 1427 | 1466 |
| LMArena Hard Prompts | 1449 | 1488 |
| LMArena Coding | 1462 | 1513 |
| LMArena WebDev | – | 1387 |
| LMArena Vision | 1232 | 1293 |
| AA Intelligence Index | 23.0 | 39.0 |
| IFBench | 73.1% | 74.0% |
| AA-LCR | 78.2% | 82.0% |
| MMMU-Pro | 74.2% | 78.4% |
| AA-Omniscience | -8.7 | 5.8 |
| Terminal-Bench Hard | 32.6% | 57.6% |
| GPQA Diamond (AA) | 85.3% | 92.0% |
| Humanity's Last Exam (AA) | 28.5% | 43.7% |
| τ²-Bench Telecom (AA) | 84.8% | 87.1% |
| PRBench Finance | 51.3% | – |
| PRBench Legal | 49.0% | – |
| VISTA | 49.7% | – |
| MultiNRC | 52.1% | – |
| HiL-Bench | – | 9.7% |
| TutorBench | 55.3% | – |
| EQ-Bench 4 | – | 1272 |
| Kagi LLM Benchmark | 72.7% | 63.8% |
| IFEval (HELM) | 87.5% | – |
| Omni-MATH (HELM) | 64.7% | – |
| WildBench (HELM) | 85.7% | – |
| MMLU-Pro (HELM) | 86.3% | – |
| GPQA Diamond (HELM) | 79.1% | – |
| HELM Capabilities mean | 80.7% | – |
| Aider Polyglot | 88.0% | – |
| SWE-bench Verified (any scaffold) | 75.6% | – |
Data as of 2026-09-12. Best configuration of each model; every score links to its source on the model pages.
GPT-5 vs GPT-5.4: questions
- Is GPT-5 better than GPT-5.4?
- GPT-5.4 leads on quality: 63.5 vs 60.8. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 is ahead overall as of 2026-09-12, but check the category scores for your use.
- Is GPT-5 better than GPT-5.4 for coding?
- GPT-5 scores higher in coding (61 vs 52 on the category index, where 50 is average).
- Is GPT-5 better than GPT-5.4 for agentic tasks?
- GPT-5.4 scores higher in agentic tasks (66 vs 51 on the category index, where 50 is average).
- Which is cheaper, GPT-5 or GPT-5.4?
- GPT-5 is cheaper: $3.44 against $5.63 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5 or GPT-5.4?
- GPT-5.4 streams faster: 132 against 85 output tokens per second.
- Which has the larger context window?
- GPT-5.4 accepts more context: 1.1M against 400k tokens.