Model comparison
DeepSeek-V3 vs MiniMax-M2.1
DeepSeek-V3 and MiniMax-M2.1 score almost the same on the Noometry Index (39.5 vs 38.9), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 18 benchmarks with published results for both. DeepSeek-V3 scores higher in 2 categories and MiniMax-M2.1 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiniMax-M2.1 leads 43.2 to 34.0.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 6.1% for DeepSeek-V3 and 11.8% for MiniMax-M2.1.
- DeepSeek-V3 is cheaper at $0.24 / $0.90 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 | MiniMax-M2.1 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 39.5 | 38.9 |
| Released | 2024-12-26 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 164K | 205K |
| Max output | 164K | 131K |
| Input $ / M tokens | $0.24 | $0.30 |
| Output $ / M tokens | $0.90 | $1.20 |
| Results tracked | 60 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 42.3 (#106), MiniMax-M2.1: 40.4 (#143)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1368 | 1421 |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1384 |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| METR Time Horizons | 49.6% | — |
Reasoning DeepSeek-V3 leads
DeepSeek-V3: 20.5 (#236), MiniMax-M2.1: 16.6 (#302)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1365 | 1411 |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 11.2% |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.94 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math MiniMax-M2.1 leads
DeepSeek-V3: 32.1 (#219), MiniMax-M2.1: 38.3 (#138)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1373 | 1397 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Too close to call
DeepSeek-V3: 37.5 (#155), MiniMax-M2.1: 38.3 (#147)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 6.1% | 11.8% |
| LMArena Expert | 1351 | 1431 |
| GPQA Diamond | 67.6% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual MiniMax-M2.1 leads
DeepSeek-V3: 48.5 (#143), MiniMax-M2.1: 50.0 (#128)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1358 | 1378 |
| LMArena Chinese | 1391 | 1430 |
| LMArena French | 1385 | 1404 |
| LMArena German | 1374 | 1381 |
| LMArena Japanese | 1333 | 1287 |
| LMArena Korean | 1319 | 1298 |
| LMArena Russian | 1373 | 1387 |
| LMArena Spanish | 1358 | 1397 |
Instruction Following MiniMax-M2.1 leads
DeepSeek-V3: 72.8 (#130), MiniMax-M2.1: 73.8 (#112)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1345 | 1400 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context MiniMax-M2.1 leads
DeepSeek-V3: 34.0 (#253), MiniMax-M2.1: 43.2 (#101)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1352 | 1416 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Too close to call
DeepSeek-V3: 57.4 (#130), MiniMax-M2.1: 58.3 (#120)
| Benchmark | DeepSeek-V3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1375 | 1392 |
| LMArena Creative Writing | 1364 | 1361 |
| LMArena Multi-Turn | 1389 | 1396 |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than MiniMax-M2.1?
DeepSeek-V3 and MiniMax-M2.1 score almost the same on the Noometry Index (39.5 vs 38.9), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3 or MiniMax-M2.1?
DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is DeepSeek-V3 or MiniMax-M2.1 better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 40.4 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 and MiniMax-M2.1 share?
18 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and MiniMax-M2.1 has 22.