Model comparison
Grok 4.7 vs MiniMax-M2.5
Grok 4.7 is the stronger model overall, scoring 46.6 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 5.7× 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.
MiniMaxSummary
- They share 16 benchmarks with published results for both. Grok 4.7 scores higher in 8 categories and MiniMax-M2.5 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 40.1 to 17.6.
- The biggest single-benchmark swing is NYT Connections (extended): 76.8% for Grok 4.7 and 16.8% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | MiniMax-M2.5 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 46.6 | 38.1 |
| Released | 2026-09-21 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | 500K | 205K |
| Max output | 500K | 131K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $6 | $1.20 |
| Results tracked | 21 | 33 |
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), MiniMax-M2.5: 47.9 (#53)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1636 | 1386 |
| LMArena Coding | 1423 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| CursorBench | 46.3% | — |
| SWE-bench Multilingual | — | 68.3% |
| FrontierSWE | 29.5% | — |
| SciCode | 57.4% | — |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Grok 4.7: —, MiniMax-M2.5: 30.2 (#70)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning Grok 4.7 leads
Grok 4.7: 40.1 (#49), MiniMax-M2.5: 17.6 (#281)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| NYT Connections (extended) | 76.8% | 16.8% |
| LMArena Hard Prompts | 1409 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | 17.7% | — |
| Epoch Capabilities Index | — | 146.68 |
Math Grok 4.7 leads
Grok 4.7: 41.1 (#73), MiniMax-M2.5: 25.8 (#242)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 34% | 4% |
| LMArena Math | 1393 | 1378 |
Knowledge Too close to call
Grok 4.7: 38.7 (#130), MiniMax-M2.5: 38.6 (#132)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1413 | 1378 |
| Vectara Hallucination Rate | — | 9.1% |
Multimodal Not comparable
Grok 4.7: 28.8 (#107), MiniMax-M2.5: —
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| Furniture Assembly | 20.8% | — |
Multilingual Grok 4.7 leads
Grok 4.7: 51.2 (#108), MiniMax-M2.5: 47.3 (#147)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1392 | 1338 |
| LMArena Chinese | 1476 | 1392 |
| LMArena Russian | 1396 | 1359 |
| LMArena French | — | 1363 |
| LMArena German | — | 1361 |
| LMArena Japanese | — | 1169 |
| LMArena Korean | — | 1232 |
| LMArena Spanish | — | 1354 |
Instruction Following Grok 4.7 leads
Grok 4.7: 74.3 (#98), MiniMax-M2.5: 71.7 (#143)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1353 |
Long Context Grok 4.7 leads
Grok 4.7: 43.2 (#97), MiniMax-M2.5: 37.4 (#211)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1416 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.1 (#23), MiniMax-M2.5: 54.1 (#149)
| Benchmark | Grok 4.7 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1397 | 1359 |
| LMArena Creative Writing | 1391 | 1331 |
| EQ-Bench Creative Writing | 2007 | 1361 |
| LMArena Multi-Turn | 1389 | 1364 |
Frequently asked questions
Is Grok 4.7 better than MiniMax-M2.5?
Grok 4.7 is the stronger model overall, scoring 46.6 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 5.7× 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 MiniMax-M2.5?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.7 lists at $2 and $6.
Is Grok 4.7 or MiniMax-M2.5 better for coding?
Grok 4.7 scores higher on coding benchmarks: 55.0 versus 47.9 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 205K.
How many benchmarks do Grok 4.7 and MiniMax-M2.5 share?
16 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and MiniMax-M2.5 has 33.