Model comparison
Mercury 2 vs MiniMax-M2
Mercury 2 is the stronger model overall, scoring 39.1 to 37.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
MiniMaxSummary
- They share 12 benchmarks with published results for both. Mercury 2 scores higher in 4 categories and MiniMax-M2 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2 leads 39.3 to 33.5.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | MiniMax-M2 | |
|---|---|---|
| Provider | Inception | MiniMax |
| Noometry Index | 39.1 | 37.4 |
| Released | 2026-02-20 | 2025-10-27 |
| 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 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Mercury 2: 33.5 (#255), MiniMax-M2: 39.3 (#159)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1171 | 1297 |
| LMArena Coding | 1391 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), MiniMax-M2: 19.4 (#258)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, MiniMax-M2: 37.3 (#160)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1352 |
Knowledge Too close to call
Mercury 2: 36.2 (#172), MiniMax-M2: 37.0 (#163)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1358 | 1337 |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), MiniMax-M2: 45.3 (#171)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1331 | 1313 |
| LMArena Chinese | 1417 | 1366 |
| LMArena Russian | 1304 | 1331 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Spanish | — | 1326 |
Instruction Following Too close to call
Mercury 2: 70.2 (#165), MiniMax-M2: 70.2 (#166)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1329 | 1328 |
Long Context Too close to call
Mercury 2: 40.5 (#154), MiniMax-M2: 40.5 (#153)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1330 | 1331 |
Writing & Preference Too close to call
Mercury 2: 53.8 (#155), MiniMax-M2: 53.0 (#162)
| Benchmark | Mercury 2 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1355 | 1340 |
| LMArena Creative Writing | 1289 | 1286 |
| LMArena Multi-Turn | 1358 | 1361 |
Frequently asked questions
Is Mercury 2 better than MiniMax-M2?
Mercury 2 is the stronger model overall, scoring 39.1 to 37.4 on the Noometry Index.
Which is cheaper, Mercury 2 or MiniMax-M2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is Mercury 2 or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 128K.
How many benchmarks do Mercury 2 and MiniMax-M2 share?
12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and MiniMax-M2 has 21.