Model comparison
GPT-5.4 nano vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 41.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GPT-5.4 nano scores higher in 1 category and MiMo-V2.5-Pro in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 55.7.
- The biggest single-benchmark swing is ProofBench: 5% for GPT-5.4 nano and 22% for MiMo-V2.5-Pro.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 400K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 41.9 | 45.2 |
| Released | 2026-03-17 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.20 | $0.43 |
| Output $ / M tokens | $1.25 | $0.87 |
| Results tracked | 40 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
GPT-5.4 nano: 43.6 (#84), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 46.9% | 50.2% |
| LMArena Coding | 1405 | 1503 |
| ALE-Bench | 1,005 | 899.8 |
| LMArena WebDev | — | 1479 |
| WeirdML | 49.2% | — |
Reasoning MiMo-V2.5-Pro leads
GPT-5.4 nano: 23.7 (#173), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 9.3% | 4% |
| LMArena Hard Prompts | 1381 | 1488 |
| DTBench | 80.3% | 84.5% |
| LMCA | 36.9% | 29.5% |
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 51.5% | — |
| Chess Puzzles | 30% | — |
| Mystery Game Puzzles | 9% | — |
| Epoch Capabilities Index | 145.81 | — |
| ForecastBench | 57.3 | — |
Math Too close to call
GPT-5.4 nano: 40.9 (#88), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 5% | 22% |
| LMArena Math | 1406 | 1481 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Too close to call
GPT-5.4 nano: 41.9 (#103), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1396 | 1503 |
| GPQA Diamond | 78.5% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
Multimodal Not comparable
GPT-5.4 nano: 36.7 (#78), MiMo-V2.5-Pro: —
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual MiMo-V2.5-Pro leads
GPT-5.4 nano: 48.6 (#140), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1359 | 1449 |
| LMArena Chinese | 1392 | 1507 |
| LMArena French | 1396 | 1488 |
| LMArena German | 1367 | 1458 |
| LMArena Japanese | 1343 | 1412 |
| LMArena Korean | 1320 | 1437 |
| LMArena Russian | 1363 | 1450 |
| LMArena Spanish | 1371 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
GPT-5.4 nano: 71.9 (#144), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1362 | 1477 |
Long Context MiMo-V2.5-Pro leads
GPT-5.4 nano: 41.6 (#137), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1366 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
GPT-5.4 nano: 55.7 (#142), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | GPT-5.4 nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1372 | 1465 |
| LMArena Creative Writing | 1314 | 1440 |
| LMArena Multi-Turn | 1382 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is GPT-5.4 nano better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 41.9 on the Noometry Index.
Which is cheaper, GPT-5.4 nano or MiMo-V2.5-Pro?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is GPT-5.4 nano or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 nano and MiMo-V2.5-Pro share?
23 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and MiMo-V2.5-Pro has 27.