Model comparison
Grok 4.6 vs MiniMax-M2.5
Grok 4.6 is the stronger model overall, scoring 56.9 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 5.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
MiniMaxSummary
- They share 25 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and MiniMax-M2.5 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 17.5.
- The biggest single-benchmark swing is NYT Connections (extended): 80% for Grok 4.6 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 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | MiniMax-M2.5 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 56.9 | 38.3 |
| Released | 2026-08-12 | 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 | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1617 | 1387 |
| LMArena Coding | 1465 | 1381 |
| ALE-Bench | 1,508 | 618.17 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| CursorBench | 41.4% | — |
| SWE-bench Multilingual | — | 68.3% |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| WeirdML | 67.3% | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| Vending-Bench 2 | 9,047 | -23.16 |
| Terminal-Bench | — | 42.7% |
| APEX-Agents | 65.3% | — |
| GDP.pdf | 17.2% | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 67.1% | 4.9% |
| NYT Connections (extended) | 80% | 16.8% |
| ARC-AGI-1 | 87.5% | 63.7% |
| LMArena Hard Prompts | 1447 | 1372 |
| Epoch Capabilities Index | 156.44 | 146.68 |
| SimpleBench | 75.9% | — |
| Kagi LLM Benchmark | — | 55.2% |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 51% | 4% |
| LMArena Math | 1423 | 1378 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1467 | 1379 |
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 49.3% | — |
| Vectara Hallucination Rate | — | 9.1% |
Multimodal Not comparable
Grok 4.6: 43.6 (#23), MiniMax-M2.5: —
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1420 | 1338 |
| LMArena Chinese | 1480 | 1393 |
| LMArena French | 1461 | 1362 |
| LMArena German | 1431 | 1362 |
| LMArena Japanese | 1376 | 1171 |
| LMArena Korean | 1397 | 1232 |
| LMArena Russian | 1422 | 1358 |
| LMArena Spanish | 1404 | 1354 |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1431 | 1353 |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1454 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Grok 4.6 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1428 | 1359 |
| LMArena Creative Writing | 1428 | 1331 |
| LMArena Multi-Turn | 1425 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
Frequently asked questions
Is Grok 4.6 better than MiniMax-M2.5?
Grok 4.6 is the stronger model overall, scoring 56.9 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 5.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.6 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 4.6 lists at $2 and $6.
Is Grok 4.6 or MiniMax-M2.5 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 48.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 205K.
How many benchmarks do Grok 4.6 and MiniMax-M2.5 share?
25 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and MiniMax-M2.5 has 33.