Model comparison
GPT-5.4 mini vs MiMo-V2-Pro
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 3.1× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. GPT-5.4 mini scores higher in 6 categories and MiMo-V2-Pro in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 41.4.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 25.8% for MiMo-V2-Pro.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.4 mini | MiMo-V2-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 45.0 | 43.0 |
| Released | 2026-03-17 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.75 | $0.43 |
| Output $ / M tokens | $4.50 | $0.87 |
| Results tracked | 46 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1397 | 1433 |
| LMArena Coding | 1438 | 1476 |
| ALE-Bench | 1,189 | 785.17 |
| FrontierCode | 27% | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.9 (#81), MiMo-V2-Pro: —
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 61.8% | 25.8% |
| Thematic Generalization | 61.7% | 45.9% |
| LMArena Hard Prompts | 1424 | 1457 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1419 | 1447 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1435 | 1478 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), MiMo-V2-Pro: —
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual Too close to call
GPT-5.4 mini: 51.9 (#96), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1405 | 1416 |
| LMArena Chinese | 1446 | 1456 |
| LMArena French | 1440 | 1469 |
| LMArena German | 1409 | 1417 |
| LMArena Japanese | 1374 | 1366 |
| LMArena Korean | 1368 | 1400 |
| LMArena Russian | 1417 | 1427 |
| LMArena Spanish | 1405 | 1457 |
Instruction Following MiMo-V2-Pro leads
GPT-5.4 mini: 74.1 (#102), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1405 | 1445 |
Long Context GPT-5.4 mini leads
GPT-5.4 mini: 43.0 (#112), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1407 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | GPT-5.4 mini | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1412 | 1436 |
| LMArena Creative Writing | 1370 | 1415 |
| LMArena Multi-Turn | 1429 | 1456 |
| EQ-Bench Creative Writing | 1665 | — |
Frequently asked questions
Is GPT-5.4 mini better than MiMo-V2-Pro?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 3.1× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 mini or MiMo-V2-Pro?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or MiMo-V2-Pro better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 43.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 mini and MiMo-V2-Pro share?
21 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and MiMo-V2-Pro has 23.