Model comparison
DeepSeek-R1 vs MiniMax M1
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 40.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 18 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and MiniMax M1 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiniMax M1 leads 26.9 to 18.6.
- The biggest single-benchmark swing is Fiction.LiveBench: 75% for DeepSeek-R1 and 69.4% for MiniMax M1.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $0.55 / $2.20 for MiniMax M1.
- MiniMax M1 accepts more context: 1M tokens versus 164K.
- MiniMax M1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | MiniMax M1 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 42.3 | 40.3 |
| Released | 2025-01-20 | 2025-06-13 |
| Weights | Proprietary | Open |
| Context window | 164K | 1M |
| Max output | 64K | 40K |
| Input $ / M tokens | $0.50 | $0.55 |
| Output $ / M tokens | $2.15 | $2.20 |
| Results tracked | 52 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), MiniMax M1: 39.9 (#153)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1427 | 1359 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), MiniMax M1: —
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning MiniMax M1 leads
DeepSeek-R1: 18.6 (#278), MiniMax M1: 26.9 (#126)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1339 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), MiniMax M1: 37.5 (#151)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Math | 1400 | 1361 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), MiniMax M1: 36.4 (#170)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1394 | 1317 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), MiniMax M1: 45.8 (#163)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1412 | 1319 |
| LMArena Chinese | 1442 | 1360 |
| LMArena French | 1417 | 1370 |
| LMArena German | 1404 | 1350 |
| LMArena Japanese | 1391 | 1217 |
| LMArena Korean | 1360 | 1266 |
| LMArena Russian | 1423 | 1329 |
| LMArena Spanish | 1411 | 1353 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), MiniMax M1: 69.3 (#174)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1312 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), MiniMax M1: 41.4 (#141)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| Fiction.LiveBench | 75% | 69.4% |
| LMArena Longer Query | 1391 | 1326 |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), MiniMax M1: 53.1 (#161)
| Benchmark | DeepSeek-R1 | MiniMax M1 |
|---|---|---|
| LMArena Text | 1428 | 1343 |
| LMArena Creative Writing | 1405 | 1298 |
| LMArena Multi-Turn | 1405 | 1335 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than MiniMax M1?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 40.3 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or MiniMax M1?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; MiniMax M1 lists at $0.55 and $2.20.
Is DeepSeek-R1 or MiniMax M1 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-R1 and MiniMax M1 share?
18 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and MiniMax M1 has 18.