Model comparison
Llama 4 Maverick vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.6 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and MiMo-V2.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.8 to 39.0.
- The biggest single-benchmark swing is SciCode: 33.1% for Llama 4 Maverick and 43.1% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 128K.
Side by side
| Llama 4 Maverick | MiMo-V2.5 | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 30.6 | 43.0 |
| Released | 2025-04-05 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 128K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.19 | $0.14 |
| Output $ / M tokens | $0.65 | $0.28 |
| Results tracked | 54 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Llama 4 Maverick: 26.3 (#318), MiMo-V2.5: 43.6 (#75)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| SciCode | 33.1% | 43.1% |
| LMArena Coding | 1302 | 1469 |
| ALE-Bench | 172.97 | 513.95 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| LMArena WebDev | — | 1438 |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 27.9 (#86), MiMo-V2.5: —
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning MiMo-V2.5 leads
Llama 4 Maverick: 10.1 (#337), MiMo-V2.5: 27.8 (#98)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| CritPt | 0% | 3.7% |
| LMArena Hard Prompts | 1281 | 1450 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math MiMo-V2.5 leads
Llama 4 Maverick: 24.6 (#256), MiMo-V2.5: 35.4 (#145)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1299 | 1436 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| ProofBench | — | 16% |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge MiMo-V2.5 leads
Llama 4 Maverick: 33.3 (#196), MiMo-V2.5: 40.2 (#109)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1259 | 1459 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal MiMo-V2.5 leads
Llama 4 Maverick: 30.9 (#100), MiMo-V2.5: 39.0 (#53)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1141 | 1245 |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual MiMo-V2.5 leads
Llama 4 Maverick: 42.4 (#190), MiMo-V2.5: 52.0 (#96)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1269 | 1404 |
| LMArena Chinese | 1277 | 1467 |
| LMArena French | 1258 | 1447 |
| LMArena German | 1291 | 1421 |
| LMArena Japanese | 1207 | 1304 |
| LMArena Korean | 1203 | 1363 |
| LMArena Russian | 1286 | 1395 |
| LMArena Spanish | 1293 | 1412 |
Instruction Following MiMo-V2.5 leads
Llama 4 Maverick: 71.9 (#140), MiMo-V2.5: 75.7 (#55)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1433 |
| IFEval | 90.8% | — |
Long Context MiMo-V2.5 leads
Llama 4 Maverick: 31.4 (#274), MiMo-V2.5: 44.1 (#69)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1280 | 1444 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference MiMo-V2.5 leads
Llama 4 Maverick: 39.0 (#247), MiMo-V2.5: 61.8 (#82)
| Benchmark | Llama 4 Maverick | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1287 | 1427 |
| LMArena Creative Writing | 1266 | 1392 |
| LMArena Multi-Turn | 1289 | 1445 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.6 on the Noometry Index.
Which is cheaper, Llama 4 Maverick or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.
Is Llama 4 Maverick or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 26.3 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 128K.
How many benchmarks do Llama 4 Maverick and MiMo-V2.5 share?
21 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and MiMo-V2.5 has 23.