Model comparison
Mercury 2 vs MiniMax-M2.1
Mercury 2 and MiniMax-M2.1 score almost the same on the Noometry Index (39.1 vs 38.9), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
MiniMaxSummary
- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 1 category and MiniMax-M2.1 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.8 to 16.6.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 128K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | MiniMax-M2.1 | |
|---|---|---|
| Provider | Inception | MiniMax |
| Noometry Index | 39.1 | 38.9 |
| Released | 2026-02-20 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | 128K | 205K |
| Max output | 50K | 131K |
| Input $ / M tokens | $0.25 | $0.30 |
| Output $ / M tokens | $0.75 | $1.20 |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Mercury 2: 33.5 (#255), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1171 | 1384 |
| LMArena Coding | 1391 | 1421 |
| ALE-Bench | 785.58 | 623.83 |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
Agentic & Tool Use Not comparable
Mercury 2: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, MiniMax-M2.1: 38.3 (#138)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | — | 1397 |
Knowledge MiniMax-M2.1 leads
Mercury 2: 36.2 (#172), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 11.8% |
| LMArena Expert | 1358 | 1431 |
Multilingual MiniMax-M2.1 leads
Mercury 2: 46.6 (#157), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1331 | 1378 |
| LMArena Chinese | 1417 | 1430 |
| LMArena Russian | 1304 | 1387 |
| LMArena French | — | 1404 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
| LMArena Spanish | — | 1397 |
Instruction Following MiniMax-M2.1 leads
Mercury 2: 70.2 (#165), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1329 | 1400 |
Long Context MiniMax-M2.1 leads
Mercury 2: 40.5 (#154), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1330 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Mercury 2: 53.8 (#155), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Mercury 2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1355 | 1392 |
| LMArena Creative Writing | 1289 | 1361 |
| LMArena Multi-Turn | 1358 | 1396 |
Frequently asked questions
Is Mercury 2 better than MiniMax-M2.1?
Mercury 2 and MiniMax-M2.1 score almost the same on the Noometry Index (39.1 vs 38.9), so choose on price, context window or the category you care about most.
Which is cheaper, Mercury 2 or MiniMax-M2.1?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is Mercury 2 or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 128K.
How many benchmarks do Mercury 2 and MiniMax-M2.1 share?
14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and MiniMax-M2.1 has 22.