Model comparison
Grok 4.6 vs MiniMax-M3
Grok 4.6 is the stronger model overall, scoring 56.9 to 43.8 on the Noometry Index. MiniMax-M3 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 . 36 shared benchmarks.
MiniMaxSummary
- They share 36 benchmarks with published results for both. Grok 4.6 scores higher in 8 categories and MiniMax-M3 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 30.1.
- The biggest single-benchmark swing is FrontierCode: 48% for Grok 4.6 and 14.7% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.6.
- MiniMax-M3 accepts more context: 1M tokens versus 500K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | MiniMax-M3 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 56.9 | 43.8 |
| Released | 2026-08-12 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 500K | 1M |
| Max output | 500K | 512K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $6 | $1.20 |
| Results tracked | 49 | 41 |
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-M3: 41.8 (#118)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| FrontierCode | 48% | 14.7% |
| LMArena WebDev | 1617 | 1482 |
| SciCode | 56.5% | 47.1% |
| LMArena Coding | 1465 | 1469 |
| ALE-Bench | 1,508 | 640.02 |
| DeepSWE | 67.5% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| WeirdML | 67.3% | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), MiniMax-M3: 22.6 (#130)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 65.3% | 37.7% |
| Vending-Bench 2 | 9,047 | 2,158 |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| GDP.pdf | 17.2% | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), MiniMax-M3: 30.1 (#87)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 75.9% | 45.8% |
| NYT Connections (extended) | 80% | 65.1% |
| CritPt | 19.7% | 3.7% |
| Chess Puzzles | 40% | 14% |
| LMArena Hard Prompts | 1447 | 1447 |
| Mystery Game Puzzles | 34% | 8% |
| DTBench | 97.3% | 78.9% |
| LMCA | 48.5% | 33.7% |
| Epoch Capabilities Index | 156.44 | 146.95 |
| ARC-AGI-2 | 67.1% | — |
| ARC-AGI-1 | 87.5% | — |
| EBR-Bench | 30.5% | — |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), MiniMax-M3: 40.0 (#95)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 71.1% |
| ProofBench | 51% | 18% |
| LMArena Math | 1423 | 1429 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), MiniMax-M3: 58.4 (#35)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 94% | 90.9% |
| LMArena Expert | 1467 | 1461 |
| SimpleQA Verified | 49.3% | — |
Multimodal Grok 4.6 leads
Grok 4.6: 43.6 (#23), MiniMax-M3: 40.2 (#51)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1263 | 1253 |
| LMArena Document | 1452 | 1435 |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
Multilingual Too close to call
Grok 4.6: 53.0 (#74), MiniMax-M3: 53.0 (#75)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1420 | 1420 |
| LMArena Chinese | 1480 | 1463 |
| LMArena French | 1461 | 1447 |
| LMArena German | 1431 | 1426 |
| LMArena Japanese | 1376 | 1381 |
| LMArena Korean | 1397 | 1372 |
| LMArena Russian | 1422 | 1428 |
| LMArena Spanish | 1404 | 1432 |
Instruction Following Too close to call
Grok 4.6: 75.4 (#63), MiniMax-M3: 75.5 (#62)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1431 | 1433 |
Long Context Too close to call
Grok 4.6: 44.5 (#66), MiniMax-M3: 44.2 (#72)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1454 | 1445 |
Writing & Preference Too close to call
Grok 4.6: 62.3 (#80), MiniMax-M3: 62.1 (#83)
| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1428 | 1433 |
| LMArena Creative Writing | 1428 | 1404 |
| LMArena Multi-Turn | 1425 | 1442 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Grok 4.6 better than MiniMax-M3?
Grok 4.6 is the stronger model overall, scoring 56.9 to 43.8 on the Noometry Index. MiniMax-M3 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-M3?
MiniMax-M3 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-M3 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 500K.
How many benchmarks do Grok 4.6 and MiniMax-M3 share?
36 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and MiniMax-M3 has 41.