Model comparison
Gemini 1.0 Pro vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 27.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
MiniMaxSummary
- They share 16 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 1 category and MiniMax-M2.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 9.3.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | MiniMax-M2.1 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 27.3 | 38.9 |
| Released | 2023-12-13 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 24 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Gemini 1.0 Pro: 32.2 (#275), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1108 | 1421 |
| LMArena WebDev | — | 1384 |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Agentic & Tool Use Not comparable
Gemini 1.0 Pro: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Too close to call
Gemini 1.0 Pro: 17.1 (#296), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 117.04 | — |
Math MiniMax-M2.1 leads
Gemini 1.0 Pro: 9.3 (#321), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1132 | 1397 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 11.2% | — |
Knowledge MiniMax-M2.1 leads
Gemini 1.0 Pro: 15.6 (#291), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1059 | 1431 |
| GPQA Diamond | 34% | — |
| Vectara Hallucination Rate | — | 11.8% |
| MMLU | 70% | — |
Multilingual MiniMax-M2.1 leads
Gemini 1.0 Pro: 33.4 (#252), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1138 | 1378 |
| LMArena Chinese | 1124 | 1430 |
| LMArena French | 1145 | 1404 |
| LMArena German | 1125 | 1381 |
| LMArena Japanese | 1023 | 1287 |
| LMArena Russian | 1186 | 1387 |
| LMArena Spanish | 1119 | 1397 |
| LMArena Korean | — | 1298 |
Instruction Following MiniMax-M2.1 leads
Gemini 1.0 Pro: 57.6 (#267), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1114 | 1400 |
Long Context MiniMax-M2.1 leads
Gemini 1.0 Pro: 34.3 (#249), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1132 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Gemini 1.0 Pro: 36.0 (#264), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Gemini 1.0 Pro | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1149 | 1392 |
| LMArena Creative Writing | 1131 | 1361 |
| LMArena Multi-Turn | 1139 | 1396 |
Frequently asked questions
Is Gemini 1.0 Pro better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and MiniMax-M2.1 share?
16 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and MiniMax-M2.1 has 22.