Model comparison
Grok 4.5 vs MiMo-V2.5-Pro
Grok 4.5 is the stronger model overall, scoring 55.0 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 5.5× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Grok 4.5 scores higher in 5 categories and MiMo-V2.5-Pro in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.5 leads 56.1 to 26.8.
- The biggest single-benchmark swing is NYT Connections (extended): 79.9% for Grok 4.5 and 34.4% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $6 for Grok 4.5.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 500K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| Grok 4.5 | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 55.0 | 45.2 |
| Released | 2026-07-08 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 500K | 1.05M |
| Max output | 500K | 131K |
| Input $ / M tokens | $2 | $0.43 |
| Output $ / M tokens | $6 | $0.87 |
| Results tracked | 52 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.5 leads
Grok 4.5: 52.2 (#35), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1553 | 1479 |
| SciCode | 54.1% | 50.2% |
| LMArena Coding | 1474 | 1503 |
| ALE-Bench | 1,309 | 899.8 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.4% | — |
| WeirdML | 46.4% | — |
Agentic & Tool Use Not comparable
Grok 4.5: 44.4 (#17), MiMo-V2.5-Pro: —
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| APEX-Agents | 56.2% | — |
| τ²-bench Banking | 47.9% | — |
| PostTrainBench | 23.4% | — |
| GBAEval | 65.4% | — |
| GDP.pdf | 14% | — |
| LMArena Search | 1213 | — |
| Vending-Bench 2 | 3,887 | — |
Reasoning Grok 4.5 leads
Grok 4.5: 56.1 (#25), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 79.9% | 34.4% |
| CritPt | 15.4% | 4% |
| LMArena Hard Prompts | 1462 | 1488 |
| DTBench | 96.5% | 84.5% |
| LMCA | 45.2% | 29.5% |
| ARC-AGI-2 | 52.6% | — |
| SimpleBench | 70% | — |
| Kagi LLM Benchmark | 83.5% | — |
| ARC-AGI-1 | 87.2% | — |
| Chess Puzzles | 36% | — |
| Surface Evolver Bench | 74.4% | — |
| Epoch Capabilities Index | 153.92 | — |
Math Grok 4.5 leads
Grok 4.5: 60.9 (#35), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 31% | 22% |
| LMArena Math | 1459 | 1481 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 24.4% | — |
| OTIS Mock AIME 2024-2025 | 97.8% | — |
Knowledge Grok 4.5 leads
Grok 4.5: 62.3 (#24), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1466 | 1503 |
| GPQA Diamond | 93.4% | — |
| SimpleQA Verified | 48.3% | — |
Multimodal Not comparable
Grok 4.5: 37.6 (#72), MiMo-V2.5-Pro: —
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1288 | — |
| Blueprint-Bench 2 | 27.3% | — |
| Furniture Assembly | 22.5% | — |
| LMArena Document | 1452 | — |
Multilingual Too close to call
Grok 4.5: 54.4 (#42), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1440 | 1449 |
| LMArena Chinese | 1496 | 1507 |
| LMArena French | 1456 | 1488 |
| LMArena German | 1446 | 1458 |
| LMArena Japanese | 1428 | 1412 |
| LMArena Korean | 1404 | 1437 |
| LMArena Russian | 1448 | 1450 |
| LMArena Spanish | 1450 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Grok 4.5: 76.0 (#48), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1446 | 1477 |
Long Context Too close to call
Grok 4.5: 44.8 (#56), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1463 | 1483 |
Writing & Preference Too close to call
Grok 4.5: 65.8 (#42), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Grok 4.5 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1448 | 1465 |
| LMArena Creative Writing | 1442 | 1440 |
| EQ-Bench Creative Writing | 1579 | 1493 |
| LMArena Multi-Turn | 1456 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Grok 4.5 better than MiMo-V2.5-Pro?
Grok 4.5 is the stronger model overall, scoring 55.0 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 5.5× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.
Which is cheaper, Grok 4.5 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Grok 4.5 lists at $2 and $6.
Is Grok 4.5 or MiMo-V2.5-Pro better for coding?
Grok 4.5 scores higher on coding benchmarks: 52.2 versus 47.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 500K.
How many benchmarks do Grok 4.5 and MiMo-V2.5-Pro share?
26 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and MiMo-V2.5-Pro has 27.