Model comparison
MiMo-V2.6-Flash vs o4-mini
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 41.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. MiMo-V2.6-Flash scores higher in 7 categories and o4-mini in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Flash leads 53.4 to 40.9.
- The biggest single-benchmark swing is CritPt: 12% for MiMo-V2.6-Flash and 0.6% for o4-mini.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 200K.
- MiMo-V2.6-Flash has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.6-Flash | o4-mini | |
|---|---|---|
| Provider | Xiaomi | OpenAI |
| Noometry Index | 48.5 | 41.6 |
| Released | 2026-09-21 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $0.14 | $1.10 |
| Output $ / M tokens | $0.28 | $4.40 |
| Results tracked | 19 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 53.4 (#30), o4-mini: 40.9 (#127)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Coding | 1504 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1637 | — |
| SciCode | 51.3% | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
MiMo-V2.6-Flash: —, o4-mini: 32.6 (#61)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 36.5 (#66), o4-mini: 24.6 (#162)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| CritPt | 12% | 0.6% |
| LMArena Hard Prompts | 1482 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 51.9 (#52), o4-mini: 40.8 (#89)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Math | 1468 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| ProofBench | 63% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
MiMo-V2.6-Flash: 42.2 (#99), o4-mini: 43.6 (#91)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Expert | 1501 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
Multimodal Too close to call
MiMo-V2.6-Flash: 40.5 (#47), o4-mini: 40.2 (#49)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Vision | 1259 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 54.0 (#51), o4-mini: 47.0 (#154)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Non-English | 1434 | 1337 |
| LMArena Chinese | 1511 | 1354 |
| LMArena French | 1475 | 1364 |
| LMArena Russian | 1409 | 1334 |
| LMArena Spanish | 1456 | 1347 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1312 |
Instruction Following MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 76.8 (#35), o4-mini: 75.2 (#68)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1463 | 1321 |
| IFEval | — | 92.8% |
Long Context Too close to call
MiMo-V2.6-Flash: 44.8 (#57), o4-mini: 45.5 (#33)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Longer Query | 1463 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 63.1 (#67), o4-mini: 54.0 (#152)
| Benchmark | MiMo-V2.6-Flash | o4-mini |
|---|---|---|
| LMArena Text | 1455 | 1353 |
| LMArena Creative Writing | 1400 | 1294 |
| LMArena Multi-Turn | 1451 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is MiMo-V2.6-Flash better than o4-mini?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 41.6 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Flash or o4-mini?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is MiMo-V2.6-Flash or o4-mini better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 200K.
How many benchmarks do MiMo-V2.6-Flash and o4-mini share?
16 benchmarks have published results for both models. MiMo-V2.6-Flash has 19 scored results on Noometry and o4-mini has 60.