Model comparison
Mercury 2 vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 39.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and MiMo-V2.6-Pro in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 33.5.
- The biggest single-benchmark swing is CritPt: 0.8% for Mercury 2 and 26.6% for MiMo-V2.6-Pro.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | Inception | Xiaomi |
| Noometry Index | 39.1 | 50.3 |
| Released | 2026-02-20 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 128K | 1.05M |
| Max output | 50K | 131K |
| Input $ / M tokens | $0.25 | $0.43 |
| Output $ / M tokens | $0.75 | $0.87 |
| Results tracked | 17 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Mercury 2: 33.5 (#255), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1171 | 1629 |
| SciCode | 38.7% | 60.9% |
| LMArena Coding | 1391 | 1534 |
| ALE-Bench | 785.58 | 1,158 |
| WeirdML | 43.2% | — |
Agentic & Tool Use Not comparable
Mercury 2: —, MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
Reasoning MiMo-V2.6-Pro leads
Mercury 2: 23.8 (#170), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 0.8% | 26.6% |
| LMArena Hard Prompts | 1362 | 1512 |
Math Not comparable
Mercury 2: —, MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | — | 70% |
| LMArena Math | — | 1494 |
Knowledge MiMo-V2.6-Pro leads
Mercury 2: 36.2 (#172), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1358 | 1543 |
| Vectara Hallucination Rate | 12.3% | — |
Multimodal Not comparable
Mercury 2: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
Mercury 2: 46.6 (#157), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1331 | 1474 |
| LMArena Chinese | 1417 | 1529 |
| LMArena Russian | 1304 | 1480 |
Instruction Following MiMo-V2.6-Pro leads
Mercury 2: 70.2 (#165), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1329 | 1493 |
Long Context MiMo-V2.6-Pro leads
Mercury 2: 40.5 (#154), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1330 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
Mercury 2: 53.8 (#155), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Mercury 2 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1355 | 1492 |
| LMArena Creative Writing | 1289 | 1468 |
| LMArena Multi-Turn | 1358 | 1464 |
Frequently asked questions
Is Mercury 2 better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 39.1 on the Noometry Index.
Which is cheaper, Mercury 2 or MiMo-V2.6-Pro?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is Mercury 2 or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 128K.
How many benchmarks do Mercury 2 and MiMo-V2.6-Pro share?
15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and MiMo-V2.6-Pro has 19.