Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and MiniMax-M2.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 25.6 to 16.6.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 37.6 | 38.9 |
| Released | 2024-09-06 | 2025-12-23 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), MiniMax-M2.1: 40.4 (#143)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1309 | 1421 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1384 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), MiniMax-M2.1: 16.6 (#302)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1411 |
| NYT Connections (extended) | — | 11.2% |
Math MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), MiniMax-M2.1: 38.3 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1288 | 1397 |
Knowledge MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), MiniMax-M2.1: 38.3 (#147)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1266 | 1431 |
| Vectara Hallucination Rate | — | 11.8% |
Multilingual MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), MiniMax-M2.1: 50.0 (#128)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1273 | 1378 |
| LMArena Chinese | 1318 | 1430 |
| LMArena French | 1289 | 1404 |
| LMArena German | 1258 | 1381 |
| LMArena Japanese | 1228 | 1287 |
| LMArena Korean | 1209 | 1298 |
| LMArena Russian | 1289 | 1387 |
| LMArena Spanish | 1248 | 1397 |
Instruction Following MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), MiniMax-M2.1: 73.8 (#112)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1400 |
Long Context MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), MiniMax-M2.1: 43.2 (#101)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1301 | 1416 |
Writing & Preference MiniMax-M2.1 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), MiniMax-M2.1: 58.3 (#120)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1294 | 1392 |
| LMArena Creative Writing | 1285 | 1361 |
| LMArena Multi-Turn | 1297 | 1396 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiniMax-M2.1 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiniMax-M2.1 has 22.