Model comparison
GPT-5.4 mini vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 45.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GPT-5.4 mini scores higher in 2 categories and MiMo-V2.6-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 42.2.
- The biggest single-benchmark swing is ProofBench: 21% for GPT-5.4 mini and 63% for MiMo-V2.6-Flash.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 400K.
- MiMo-V2.6-Flash has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 mini | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 45.0 | 48.5 |
| Released | 2026-03-17 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.75 | $0.14 |
| Output $ / M tokens | $4.50 | $0.28 |
| Results tracked | 46 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
GPT-5.4 mini: 45.2 (#72), MiMo-V2.6-Flash: 53.4 (#30)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena WebDev | 1397 | 1637 |
| SciCode | 49.9% | 51.3% |
| LMArena Coding | 1438 | 1504 |
| FrontierCode | 27% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.9 (#81), MiMo-V2.6-Flash: —
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
Reasoning MiMo-V2.6-Flash leads
GPT-5.4 mini: 30.4 (#85), MiMo-V2.6-Flash: 36.5 (#66)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| CritPt | 10% | 12% |
| LMArena Hard Prompts | 1424 | 1482 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |
Math MiMo-V2.6-Flash leads
GPT-5.4 mini: 45.5 (#75), MiMo-V2.6-Flash: 51.9 (#52)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| ProofBench | 21% | 63% |
| LMArena Math | 1419 | 1468 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| 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-V2.6-Flash: 42.2 (#99)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1435 | 1501 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Too close to call
GPT-5.4 mini: 39.7 (#56), MiMo-V2.6-Flash: 40.5 (#47)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | 1245 | 1259 |
Multilingual MiMo-V2.6-Flash leads
GPT-5.4 mini: 51.9 (#96), MiMo-V2.6-Flash: 54.0 (#51)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1405 | 1434 |
| LMArena Chinese | 1446 | 1511 |
| LMArena French | 1440 | 1475 |
| LMArena Russian | 1417 | 1409 |
| LMArena Spanish | 1405 | 1456 |
| LMArena German | 1409 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1368 | — |
Instruction Following MiMo-V2.6-Flash leads
GPT-5.4 mini: 74.1 (#102), MiMo-V2.6-Flash: 76.8 (#35)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1405 | 1463 |
Long Context MiMo-V2.6-Flash leads
GPT-5.4 mini: 43.0 (#112), MiMo-V2.6-Flash: 44.8 (#57)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1407 | 1463 |
Writing & Preference Too close to call
GPT-5.4 mini: 64.0 (#58), MiMo-V2.6-Flash: 63.1 (#67)
| Benchmark | GPT-5.4 mini | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1412 | 1455 |
| LMArena Creative Writing | 1370 | 1400 |
| LMArena Multi-Turn | 1429 | 1451 |
| EQ-Bench Creative Writing | 1665 | — |
Frequently asked questions
Is GPT-5.4 mini better than MiMo-V2.6-Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 45.0 on the Noometry Index.
Which is cheaper, GPT-5.4 mini or MiMo-V2.6-Flash?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or MiMo-V2.6-Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 45.2 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 mini and MiMo-V2.6-Flash share?
19 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and MiMo-V2.6-Flash has 19.