Model comparison
Grok 4.7 vs MiMo-V2.5
Grok 4.7 is the stronger model overall, scoring 46.6 to 43.0 on the Noometry Index. MiMo-V2.5 costs 17× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Grok 4.7 scores higher in 4 categories and MiMo-V2.5 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 40.1 to 27.8.
- The biggest single-benchmark swing is ProofBench: 34% for Grok 4.7 and 16% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $2 / $6 for Grok 4.7.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 500K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | MiMo-V2.5 | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 46.6 | 43.0 |
| Released | 2026-09-21 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 500K | 1.05M |
| Max output | 500K | 131K |
| Input $ / M tokens | $2 | $0.14 |
| Output $ / M tokens | $6 | $0.28 |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Grok 4.7: 55.0 (#23), MiMo-V2.5: 43.6 (#75)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1636 | 1438 |
| SciCode | 57.4% | 43.1% |
| LMArena Coding | 1423 | 1469 |
| CursorBench | 46.3% | — |
| FrontierSWE | 29.5% | — |
| ALE-Bench | — | 513.95 |
Reasoning Grok 4.7 leads
Grok 4.7: 40.1 (#49), MiMo-V2.5: 27.8 (#98)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| CritPt | 17.7% | 3.7% |
| LMArena Hard Prompts | 1409 | 1450 |
| NYT Connections (extended) | 76.8% | — |
Math Grok 4.7 leads
Grok 4.7: 41.1 (#73), MiMo-V2.5: 35.4 (#145)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| ProofBench | 34% | 16% |
| LMArena Math | 1393 | 1436 |
Knowledge MiMo-V2.5 leads
Grok 4.7: 38.7 (#130), MiMo-V2.5: 40.2 (#109)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1413 | 1459 |
Multimodal MiMo-V2.5 leads
Grok 4.7: 28.8 (#107), MiMo-V2.5: 39.0 (#53)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |
| Furniture Assembly | 20.8% | — |
Multilingual Too close to call
Grok 4.7: 51.2 (#108), MiMo-V2.5: 52.0 (#96)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1392 | 1404 |
| LMArena Chinese | 1476 | 1467 |
| LMArena Russian | 1396 | 1395 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1304 |
| LMArena Korean | — | 1363 |
| LMArena Spanish | — | 1412 |
Instruction Following MiMo-V2.5 leads
Grok 4.7: 74.3 (#98), MiMo-V2.5: 75.7 (#55)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1433 |
Long Context Too close to call
Grok 4.7: 43.2 (#97), MiMo-V2.5: 44.1 (#69)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1416 | 1444 |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.1 (#23), MiMo-V2.5: 61.8 (#82)
| Benchmark | Grok 4.7 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1397 | 1427 |
| LMArena Creative Writing | 1391 | 1392 |
| LMArena Multi-Turn | 1389 | 1445 |
| EQ-Bench Creative Writing | 2007 | — |
Frequently asked questions
Is Grok 4.7 better than MiMo-V2.5?
Grok 4.7 is the stronger model overall, scoring 46.6 to 43.0 on the Noometry Index. MiMo-V2.5 costs 17× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, Grok 4.7 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; Grok 4.7 lists at $2 and $6.
Is Grok 4.7 or MiMo-V2.5 better for coding?
Grok 4.7 scores higher on coding benchmarks: 55.0 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 500K.
How many benchmarks do Grok 4.7 and MiMo-V2.5 share?
16 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and MiMo-V2.5 has 23.