GPT-5.4 Pro vs MiMo-V2.5-Pro
GPT-5.4 Pro 
MiMo-V2.5-Pro Verdict
- GPT-5.4 Pro leads on quality: 64.3 vs 57.7.
- GPT-5.4 Pro is stronger in knowledge, multimodal, reasoning.
- MiMo-V2.5-Pro is stronger in instruction following, agents & tools, coding, composite, human preference, long context, maths.
- MiMo-V2.5-Pro is 103× cheaper ($0.653 vs $67.50 per 1M blended).
- MiMo-V2.5-Pro streams 44.8× faster (45 vs 1 tokens per second).
| Metric | GPT-5.4 Pro | MiMo-V2.5-Pro |
|---|---|---|
| BenchLeader Index | 64.3 | 57.7 |
| Instruction following score | 67.3 | 74.0 |
| Knowledge score | 73.6 | 56.7 |
| Multimodal score | 69.8 | – |
| Reasoning score | 75.3 | 67.3 |
| Agents & tools score | – | 49.0 |
| Coding score | – | 58.3 |
| Composite score | – | 56.8 |
| Human preference score | – | 61.6 |
| Long context score | – | 63.9 |
| Maths score | – | 43.0 |
| Blended price $/M | $67.50 | $0.653 |
| Output speed | 1 tok/s | 45 tok/s |
| Time to first answer | 6.3 s | 52.6 s |
| Context window | 1.1M | 1.0M |
| Humanity's Last Exam | 44.3% | – |
| SimpleBench | 74.1% | – |
| SciCode | – | 50.2% |
| ProofBench | – | 22.0% |
| Epoch Capabilities Index | 158.9 | – |
| LMArena Text | – | 1468 |
| LMArena Hard Prompts | – | 1496 |
| LMArena Coding | – | 1521 |
| LMArena WebDev | – | 1475 |
| LMArena Agent | – | -5.4 |
| AA Intelligence Index | – | 26.4 |
| IFBench | – | 79.9% |
| AA-LCR | – | 79.7% |
| AA-Omniscience | – | 3.3 |
| Terminal-Bench Hard | – | 43.2% |
| GPQA Diamond (AA) | – | 86.6% |
| Humanity's Last Exam (AA) | – | 35.7% |
| SciCode (AA) | – | 50.6% |
| τ²-Bench Telecom (AA) | – | 94.2% |
| LiveCodeBench | – | 81.3% |
| MMLU-Pro | – | 84.6% |
| LegalBench | – | 77.1% |
| CorpFin | – | 61.4% |
| TaxEval | – | 73.8% |
| Terminal-Bench 2.1 (Vals) | – | 57.3% |
| SWE-bench (Vals) | – | 74.0% |
| GPQA Diamond (Vals) | – | 82.6% |
| Vals Index | – | 41.0 |
| MultiChallenge | 69.2% | – |
| VISTA | 53.9% | – |
| MultiNRC | 62.3% | – |
| TutorBench | 56.6% | – |
| EQ-Bench 4 | – | 1208 |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
GPT-5.4 Pro vs MiMo-V2.5-Pro: questions
- Is GPT-5.4 Pro better than MiMo-V2.5-Pro?
- GPT-5.4 Pro leads on quality: 64.3 vs 57.7. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 Pro is ahead overall as of 2026-09-13, but check the category scores for your use.
- Which is cheaper, GPT-5.4 Pro or MiMo-V2.5-Pro?
- MiMo-V2.5-Pro is cheaper: $0.653 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.4 Pro or MiMo-V2.5-Pro?
- MiMo-V2.5-Pro streams faster: 45 against 1 output tokens per second.
- Which has the larger context window?
- GPT-5.4 Pro accepts more context: 1.1M against 1.0M tokens.