Model comparison
Grok 3 vs MiniMax-M2.1
Grok 3 is the stronger model overall, scoring 39.6 to 38.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
MiniMaxSummary
- They share 18 benchmarks with published results for both. Grok 3 scores higher in 6 categories and MiniMax-M2.1 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.0 to 37.7.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.8% for Grok 3 and 11.8% for MiniMax-M2.1.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | MiniMax-M2.1 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 39.6 | 38.4 |
| Released | 2025-04-09 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 40 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), MiniMax-M2.1: 40.1 (#132)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1432 | 1421 |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1384 |
| WeirdML | 37.2% | — |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.2 (#69), MiniMax-M2.1: 27.7 (#91)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| BALROG | 29.5% | — |
Reasoning MiniMax-M2.1 leads
Grok 3: 13.8 (#322), MiniMax-M2.1: 15.8 (#301)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1410 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 11.2% |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.34 | — |
Math Too close to call
Grok 3: 36.2 (#122), MiniMax-M2.1: 35.6 (#142)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1390 | 1396 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), MiniMax-M2.1: 37.7 (#143)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 5.8% | 11.8% |
| LMArena Expert | 1420 | 1432 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), MiniMax-M2.1: 50.2 (#123)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1411 | 1378 |
| LMArena Chinese | 1448 | 1430 |
| LMArena French | 1460 | 1405 |
| LMArena German | 1431 | 1380 |
| LMArena Japanese | 1389 | 1287 |
| LMArena Korean | 1374 | 1297 |
| LMArena Russian | 1416 | 1386 |
| LMArena Spanish | 1417 | 1396 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), MiniMax-M2.1: 74.0 (#108)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1399 |
| IFEval | 88.4% | — |
Long Context MiniMax-M2.1 leads
Grok 3: 38.7 (#187), MiniMax-M2.1: 43.2 (#98)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1439 | 1416 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference MiniMax-M2.1 leads
Grok 3: 56.0 (#136), MiniMax-M2.1: 58.5 (#114)
| Benchmark | Grok 3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1426 | 1392 |
| LMArena Creative Writing | 1414 | 1362 |
| LMArena Multi-Turn | 1424 | 1396 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than MiniMax-M2.1?
Grok 3 is the stronger model overall, scoring 39.6 to 38.4 on the Noometry Index.
Is Grok 3 or MiniMax-M2.1 better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 40.1 in the Noometry coding category.
How many benchmarks do Grok 3 and MiniMax-M2.1 share?
18 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and MiniMax-M2.1 has 22.