Model comparison
Grok 4.3 vs MiniMax-M2.1
Grok 4.3 is the stronger model overall, scoring 43.8 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 3.0× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
MiniMaxSummary
- They share 20 benchmarks with published results for both. Grok 4.3 scores higher in 6 categories and MiniMax-M2.1 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 16.6.
- The biggest single-benchmark swing is NYT Connections (extended): 55.2% for Grok 4.3 and 11.2% for MiniMax-M2.1.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Grok 4.3 accepts more context: 1M tokens versus 205K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.3 | MiniMax-M2.1 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 43.8 | 38.9 |
| Released | 2026-04-17 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | 1M | 205K |
| Max output | 30K | 131K |
| Input $ / M tokens | $1.25 | $0.30 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 40 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
Grok 4.3: 41.6 (#121), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1357 | 1384 |
| LMArena Coding | 1415 | 1421 |
| ALE-Bench | 944.17 | 623.83 |
| SciCode | 47.3% | — |
| WeirdML | 49.9% | — |
Agentic & Tool Use Too close to call
Grok 4.3: 27.7 (#99), MiniMax-M2.1: 27.9 (#98)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 35.9 (#68), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| NYT Connections (extended) | 55.2% | 11.2% |
| LMArena Hard Prompts | 1396 | 1411 |
| CritPt | 8% | — |
| Chess Puzzles | 25% | — |
| DTBench | 90.7% | — |
| LMCA | 38.3% | — |
| Epoch Capabilities Index | 149.16 | — |
| ForecastBench | 60.3 | — |
Math Grok 4.3 leads
Grok 4.3: 46.0 (#74), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1388 | 1397 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 11% | — |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#62), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1385 | 1431 |
| GPQA Diamond | 88.8% | — |
| SimpleQA Verified | 33.2% | — |
| Vectara Hallucination Rate | — | 11.8% |
Multimodal Not comparable
Grok 4.3: 31.6 (#104), MiniMax-M2.1: —
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1229 | — |
| Blueprint-Bench 2 | 0% | — |
Multilingual Too close to call
Grok 4.3: 50.5 (#120), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1385 | 1378 |
| LMArena Chinese | 1422 | 1430 |
| LMArena French | 1412 | 1404 |
| LMArena German | 1395 | 1381 |
| LMArena Japanese | 1379 | 1287 |
| LMArena Korean | 1356 | 1298 |
| LMArena Russian | 1399 | 1387 |
| LMArena Spanish | 1398 | 1397 |
Instruction Following MiniMax-M2.1 leads
Grok 4.3: 72.1 (#140), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1366 | 1400 |
Long Context Too close to call
Grok 4.3: 42.5 (#123), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1393 | 1416 |
Writing & Preference Too close to call
Grok 4.3: 58.5 (#118), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Grok 4.3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1397 | 1392 |
| LMArena Creative Writing | 1380 | 1361 |
| LMArena Multi-Turn | 1406 | 1396 |
| EQ-Bench 4 | 1075 | — |
Frequently asked questions
Is Grok 4.3 better than MiniMax-M2.1?
Grok 4.3 is the stronger model overall, scoring 43.8 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 3.0× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Which is cheaper, Grok 4.3 or MiniMax-M2.1?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is Grok 4.3 or MiniMax-M2.1 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 40.4 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 205K.
How many benchmarks do Grok 4.3 and MiniMax-M2.1 share?
20 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and MiniMax-M2.1 has 22.