Model comparison
DeepSeek LLM 67B vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and MiniMax-M2.1 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.1 leads 38.3 to 7.0.
Side by side
| DeepSeek LLM 67B | MiniMax-M2.1 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 24.9 | 38.9 |
| Released | 2023-11-29 | 2025-12-23 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 15 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
DeepSeek LLM 67B: 31.9 (#278), MiniMax-M2.1: 40.4 (#143)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1096 | 1421 |
| LMArena WebDev | — | 1384 |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Too close to call
DeepSeek LLM 67B: 16.5 (#304), MiniMax-M2.1: 16.6 (#302)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math MiniMax-M2.1 leads
DeepSeek LLM 67B: 8.7 (#324), MiniMax-M2.1: 38.3 (#138)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1108 | 1397 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge MiniMax-M2.1 leads
DeepSeek LLM 67B: 7.0 (#313), MiniMax-M2.1: 38.3 (#147)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1431 |
Multilingual MiniMax-M2.1 leads
DeepSeek LLM 67B: 29.4 (#267), MiniMax-M2.1: 50.0 (#128)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1073 | 1378 |
| LMArena Chinese | 1132 | 1430 |
| LMArena French | — | 1404 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1387 |
| LMArena Spanish | — | 1397 |
Instruction Following MiniMax-M2.1 leads
DeepSeek LLM 67B: 55.4 (#277), MiniMax-M2.1: 73.8 (#112)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1400 |
Long Context MiniMax-M2.1 leads
DeepSeek LLM 67B: 33.1 (#265), MiniMax-M2.1: 43.2 (#101)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1092 | 1416 |
Writing & Preference MiniMax-M2.1 leads
DeepSeek LLM 67B: 31.6 (#282), MiniMax-M2.1: 58.3 (#120)
| Benchmark | DeepSeek LLM 67B | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1105 | 1392 |
| LMArena Creative Writing | 1067 | 1361 |
| LMArena Multi-Turn | 1082 | 1396 |
Frequently asked questions
Is DeepSeek LLM 67B better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and MiniMax-M2.1 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and MiniMax-M2.1 has 22.