GPT-5 Pro vs o3
GPT-5 Pro Verdict
- GPT-5 Pro and o3 are level on quality (60.8 vs 61.6).
- GPT-5 Pro is stronger in knowledge, multimodal.
- o3 is stronger in reasoning, agents & tools, coding, composite, human preference, instruction following, long context, maths.
- o3 is 12× cheaper ($3.50 vs $41.25 per 1M blended).
| Metric | GPT-5 Pro | o3 |
|---|---|---|
| BenchLeader Index | 60.8 | 61.6 |
| Knowledge score | 68.0 | 58.0 |
| Multimodal score | 67.4 | 57.9 |
| Reasoning score | 57.6 | 61.5 |
| Agents & tools score | – | 70.3 |
| Coding score | – | 62.0 |
| Composite score | – | 54.5 |
| Human preference score | – | 62.3 |
| Instruction following score | – | 65.0 |
| Long context score | – | 63.8 |
| Maths score | – | 78.6 |
| Blended price $/M | $41.25 | $3.50 |
| Output speed | – | 107 tok/s |
| Time to first answer | – | 6.3 s |
| Context window | 400k | 200k |
| Humanity's Last Exam | 31.6% | – |
| SimpleBench | 61.6% | – |
| Epoch Capabilities Index | 150.3 | 146.9 |
| LMArena Text | – | 1432 |
| LMArena Hard Prompts | – | 1441 |
| LMArena Coding | – | 1460 |
| LMArena Vision | – | 1214 |
| AA Intelligence Index | – | 20.2 |
| IFBench | – | 71.4% |
| AA-LCR | – | 74.7% |
| MMMU-Pro | – | 70.1% |
| AA-Omniscience | – | -15.6 |
| Terminal-Bench Hard | – | 37.1% |
| GPQA Diamond (AA) | – | 82.7% |
| Humanity's Last Exam (AA) | – | 20.1% |
| τ²-Bench Telecom (AA) | – | 80.7% |
| PRBench Finance | 51.1% | 47.7% |
| PRBench Legal | 49.9% | 48.6% |
| VISTA | 52.4% | – |
| MultiNRC | 65.2% | – |
| MMMU (validation) | – | 82.9% |
| MMMU-Pro (official) | – | 76.4% |
| Kagi LLM Benchmark | 76.8% | 67.6% |
| IFEval (HELM) | – | 86.9% |
| Omni-MATH (HELM) | – | 71.4% |
| WildBench (HELM) | – | 86.1% |
| MMLU-Pro (HELM) | – | 85.9% |
| GPQA Diamond (HELM) | – | 75.3% |
| HELM Capabilities mean | – | 81.1% |
| Aider Polyglot | – | 81.3% |
| SWE-bench Verified (bash only) | – | 58.4% |
| SWE-bench Verified (any scaffold) | – | 58.4% |
| ARC-AGI-1 | 70.2% | – |
| ARC-AGI-2 | 18.3% | – |
| BFCL Overall | – | 63.0% |
Data as of 2026-09-12. Best configuration of each model; every score links to its source on the model pages.
GPT-5 Pro vs o3: questions
- Is GPT-5 Pro better than o3?
- GPT-5 Pro and o3 are level on quality (60.8 vs 61.6). The BenchLeader Index combines every independent quality benchmark; o3 is ahead overall as of 2026-09-12, but check the category scores for your use.
- Which is cheaper, GPT-5 Pro or o3?
- o3 is cheaper: $3.50 against $41.25 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- GPT-5 Pro accepts more context: 400k against 200k tokens.