Model comparison
Grok 3 vs MiniMax-M2
Grok 3 is the stronger model overall, scoring 39.9 to 37.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMaxSummary
- They share 16 benchmarks with published results for both. Grok 3 scores higher in 7 categories and MiniMax-M2 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 37.0.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | MiniMax-M2 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 39.9 | 37.4 |
| Released | 2025-04-09 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 40 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), MiniMax-M2: 39.3 (#159)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1432 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1297 |
| WeirdML | 37.2% | — |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.5 (#76), MiniMax-M2: 25.1 (#109)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| BALROG | 29.5% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Grok 3: 13.7 (#333), MiniMax-M2: 19.4 (#258)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 61.3% | 57.8% |
| LMArena Hard Prompts | 1434 | 1357 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.33 | — |
Math Too close to call
Grok 3: 38.0 (#145), MiniMax-M2: 37.3 (#160)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1391 | 1352 |
| 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: 46.2 (#82), MiniMax-M2: 37.0 (#163)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1421 | 1337 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), MiniMax-M2: 45.3 (#171)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1410 | 1313 |
| LMArena Chinese | 1448 | 1366 |
| LMArena French | 1460 | 1335 |
| LMArena German | 1431 | 1355 |
| LMArena Russian | 1416 | 1331 |
| LMArena Spanish | 1417 | 1326 |
| LMArena Japanese | 1387 | — |
| LMArena Korean | 1373 | — |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), MiniMax-M2: 70.2 (#166)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1328 |
| IFEval | 88.4% | — |
Long Context MiniMax-M2 leads
Grok 3: 38.7 (#192), MiniMax-M2: 40.5 (#153)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1439 | 1331 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), MiniMax-M2: 53.0 (#162)
| Benchmark | Grok 3 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1426 | 1340 |
| LMArena Creative Writing | 1414 | 1286 |
| LMArena Multi-Turn | 1425 | 1361 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than MiniMax-M2?
Grok 3 is the stronger model overall, scoring 39.9 to 37.4 on the Noometry Index.
Is Grok 3 or MiniMax-M2 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 39.3 in the Noometry coding category.
How many benchmarks do Grok 3 and MiniMax-M2 share?
16 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and MiniMax-M2 has 21.