Model comparison
Llama 4 Maverick vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 1.8× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
MetaSummary
- They share 16 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and MiMo-V2.6-Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 10.1.
- The biggest single-benchmark swing is SciCode: 33.1% for Llama 4 Maverick and 60.9% for MiMo-V2.6-Pro.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.
Side by side
| Llama 4 Maverick | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 30.9 | 50.3 |
| Released | 2025-04-05 | 2026-09-21 |
| Weights | Open | Open |
| Context window | 128K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.19 | $0.43 |
| Output $ / M tokens | $0.65 | $0.87 |
| Results tracked | 54 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Llama 4 Maverick: 26.6 (#324), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| SciCode | 33.1% | 60.9% |
| LMArena Coding | 1302 | 1534 |
| ALE-Bench | 172.97 | 1,158 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| LMArena WebDev | — | 1629 |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
Llama 4 Maverick: 28.2 (#91), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning MiMo-V2.6-Pro leads
Llama 4 Maverick: 10.1 (#342), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 0% | 26.6% |
| LMArena Hard Prompts | 1281 | 1512 |
| 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-V2.6-Pro leads
Llama 4 Maverick: 26.0 (#262), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1299 | 1494 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| ProofBench | — | 70% |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge MiMo-V2.6-Pro leads
Llama 4 Maverick: 33.4 (#204), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1259 | 1543 |
| 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-V2.6-Pro leads
Llama 4 Maverick: 31.6 (#105), MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1142 | 1264 |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual MiMo-V2.6-Pro leads
Llama 4 Maverick: 42.2 (#195), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1269 | 1474 |
| LMArena Chinese | 1277 | 1529 |
| LMArena Russian | 1286 | 1480 |
| LMArena French | 1259 | — |
| LMArena German | 1291 | — |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1293 | — |
Instruction Following MiMo-V2.6-Pro leads
Llama 4 Maverick: 71.7 (#146), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1267 | 1493 |
| IFEval | 90.8% | — |
Long Context MiMo-V2.6-Pro leads
Llama 4 Maverick: 31.4 (#279), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1280 | 1501 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference MiMo-V2.6-Pro leads
Llama 4 Maverick: 38.8 (#252), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Llama 4 Maverick | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1287 | 1492 |
| LMArena Creative Writing | 1267 | 1468 |
| LMArena Multi-Turn | 1289 | 1464 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 1.8× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or MiMo-V2.6-Pro?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is Llama 4 Maverick or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 128K.
How many benchmarks do Llama 4 Maverick and MiMo-V2.6-Pro share?
16 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and MiMo-V2.6-Pro has 19.