Claude Opus 4.5 vs GPT-5.4
Claude Opus 4.5 
GPT-5.4 Verdict
- GPT-5.4 leads on quality: 63.5 vs 60.7.
- Claude Opus 4.5 (thinking) is stronger in agents & tools, coding, maths.
- GPT-5.4 is stronger in composite, instruction following, knowledge, long context, multimodal, reasoning, human preference.
- GPT-5.4 is 1.8× cheaper ($5.63 vs $10.00 per 1M blended).
- GPT-5.4 streams 2.9× faster (129 vs 45 tokens per second).
| Metric | Claude Opus 4.5 (thinking) | GPT-5.4 |
|---|---|---|
| BenchLeader Index | 60.7 | 63.5 |
| Agents & tools score | 74.6 | 66.2 |
| Coding score | 56.4 | 51.6 |
| Composite score | 65.8 | 78.3 |
| Instruction following score | 54.8 | 71.9 |
| Knowledge score | 61.0 | 66.9 |
| Long context score | 65.2 | 67.6 |
| Maths score | 64.0 | – |
| Multimodal score | 58.0 | 64.0 |
| Reasoning score | 58.6 | 62.6 |
| Human preference score | – | 64.7 |
| Blended price $/M | $10.00 | $5.63 |
| Output speed | 45 tok/s | 129 tok/s |
| Time to first answer | 17.3 s | 124.6 s |
| Context window | 200k | 1.1M |
| Terminal-Bench | – | 81.8% |
| APEX-Agents | – | 34.9% |
| Epoch Capabilities Index | – | 156.9 |
| LMArena Text | – | 1466 |
| LMArena Hard Prompts | – | 1488 |
| LMArena Coding | – | 1514 |
| LMArena WebDev | – | 1386 |
| LMArena Vision | – | 1293 |
| AA Intelligence Index | 29.1 | 39.0 |
| IFBench | 58.0% | 74.0% |
| AA-LCR | 77.3% | 82.0% |
| MMMU-Pro | 74.0% | 78.4% |
| AA-Omniscience | 14 | 5.8 |
| Terminal-Bench Hard | 47.0% | 57.6% |
| GPQA Diamond (AA) | 86.6% | 92.0% |
| Humanity's Last Exam (AA) | 30.1% | 43.7% |
| τ²-Bench Telecom (AA) | 89.5% | 87.1% |
| AIME (Vals) | 95.4% | – |
| LiveCodeBench | 83.7% | – |
| MMLU-Pro | 87.3% | – |
| IOI | 20.3% | – |
| LegalBench | 84.6% | – |
| CorpFin | 65.1% | – |
| TaxEval | 74.9% | – |
| MedQA | 95.9% | – |
| MGSM | 95.2% | – |
| SWE-bench (Vals) | 76.4% | – |
| GPQA Diamond (Vals) | 85.9% | – |
| MultiChallenge | 59.0% | – |
| PRBench Finance | 46.2% | – |
| PRBench Legal | 44.2% | – |
| VISTA | 46.4% | – |
| MultiNRC | 48.6% | – |
| HiL-Bench | – | 9.7% |
| TutorBench | 51.2% | – |
| EQ-Bench 4 | – | 1272 |
| Kagi LLM Benchmark | 80.2% | 63.8% |
| ARC-AGI-1 | 80.0% | – |
| ARC-AGI-2 | 37.6% | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.5 vs GPT-5.4: questions
- Is Claude Opus 4.5 better than GPT-5.4?
- GPT-5.4 leads on quality: 63.5 vs 60.7. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Opus 4.5 better than GPT-5.4 for coding?
- Claude Opus 4.5 scores higher in coding (56 vs 52 on the category index, where 50 is average).
- Is Claude Opus 4.5 better than GPT-5.4 for agentic tasks?
- Claude Opus 4.5 scores higher in agentic tasks (75 vs 66 on the category index, where 50 is average).
- Which is cheaper, Claude Opus 4.5 or GPT-5.4?
- GPT-5.4 is cheaper: $5.63 against $10.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.5 or GPT-5.4?
- GPT-5.4 streams faster: 129 against 45 output tokens per second.
- Which has the larger context window?
- GPT-5.4 accepts more context: 1.1M against 200k tokens.