Model comparison
DeepSeek-V3.1-Terminus vs MiniMax-M2.1
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 38.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and MiniMax-M2.1 in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 15.8.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 164K.
Side by side
| DeepSeek-V3.1-Terminus | MiniMax-M2.1 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 42.6 | 38.4 |
| Released | 2025-09-22 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 164K | 205K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $1 | $1.20 |
| Results tracked | 16 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), MiniMax-M2.1: 40.1 (#132)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1426 | 1421 |
| ALE-Bench | 745.17 | 623.83 |
| LMArena WebDev | — | 1384 |
| SciCode | 40.6% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, MiniMax-M2.1: 27.7 (#91)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), MiniMax-M2.1: 15.8 (#301)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1410 |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 11.2% |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 35.7 (#138), MiniMax-M2.1: 35.6 (#142)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1402 | 1396 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, MiniMax-M2.1: 37.7 (#143)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1432 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), MiniMax-M2.1: 50.2 (#123)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1407 | 1378 |
| LMArena Russian | 1434 | 1386 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1405 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1297 |
| LMArena Spanish | — | 1396 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.4 (#96), MiniMax-M2.1: 74.0 (#108)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1399 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.5 (#88), MiniMax-M2.1: 43.2 (#98)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1426 | 1416 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), MiniMax-M2.1: 58.5 (#114)
| Benchmark | DeepSeek-V3.1-Terminus | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1420 | 1392 |
| LMArena Creative Writing | 1404 | 1362 |
| LMArena Multi-Turn | 1411 | 1396 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than MiniMax-M2.1?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 38.4 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or MiniMax-M2.1?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is DeepSeek-V3.1-Terminus or MiniMax-M2.1 better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and MiniMax-M2.1 share?
11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and MiniMax-M2.1 has 22.