Model comparison
Deepseek Coder v2 vs MiniMax M1
MiniMax M1 is the stronger model overall, scoring 40.3 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and MiniMax M1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax M1 leads 53.1 to 38.2.
Side by side
| Deepseek Coder v2 | MiniMax M1 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 35.9 | 40.3 |
| Released | 2024-06-17 | 2025-06-13 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 40K |
| Input $ / M tokens | — | $0.55 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
Deepseek Coder v2: 38.1 (#183), MiniMax M1: 39.9 (#153)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1251 | 1359 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning MiniMax M1 leads
Deepseek Coder v2: 23.6 (#176), MiniMax M1: 26.9 (#126)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1339 |
| WinoGrande | 83.7% | — |
Math MiniMax M1 leads
Deepseek Coder v2: 34.9 (#190), MiniMax M1: 37.5 (#151)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Math | 1241 | 1361 |
| GSM8K | 94.5% | — |
Knowledge MiniMax M1 leads
Deepseek Coder v2: 32.3 (#212), MiniMax M1: 36.4 (#170)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1181 | 1317 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual MiniMax M1 leads
Deepseek Coder v2: 36.3 (#240), MiniMax M1: 45.8 (#163)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1182 | 1319 |
| LMArena Chinese | 1201 | 1360 |
| LMArena French | 1185 | 1370 |
| LMArena German | 1164 | 1350 |
| LMArena Japanese | 1126 | 1217 |
| LMArena Korean | 1104 | 1266 |
| LMArena Russian | 1188 | 1329 |
| LMArena Spanish | 1153 | 1353 |
Instruction Following MiniMax M1 leads
Deepseek Coder v2: 61.7 (#242), MiniMax M1: 69.3 (#174)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1312 |
Long Context MiniMax M1 leads
Deepseek Coder v2: 37.0 (#224), MiniMax M1: 41.4 (#141)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Longer Query | 1219 | 1326 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference MiniMax M1 leads
Deepseek Coder v2: 38.2 (#253), MiniMax M1: 53.1 (#161)
| Benchmark | Deepseek Coder v2 | MiniMax M1 |
|---|---|---|
| LMArena Text | 1191 | 1343 |
| LMArena Creative Writing | 1120 | 1298 |
| LMArena Multi-Turn | 1177 | 1335 |
Frequently asked questions
Is Deepseek Coder v2 better than MiniMax M1?
MiniMax M1 is the stronger model overall, scoring 40.3 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or MiniMax M1 better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and MiniMax M1 share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and MiniMax M1 has 18.