Model comparison
DeepSeek-R1 vs MiMo-V2.5
DeepSeek-R1 and MiMo-V2.5 score almost the same on the Noometry Index (42.0 vs 43.0), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
DeepSeekSummary
- They share 20 benchmarks with published results for both. DeepSeek-R1 scores higher in 5 categories and MiMo-V2.5 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 27.8 to 18.7.
- The biggest single-benchmark swing is SciCode: 35.7% for DeepSeek-R1 and 43.1% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 164K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | MiMo-V2.5 | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 42.0 | 43.0 |
| Released | 2025-01-20 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 164K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $0.50 | $0.14 |
| Output $ / M tokens | $2.15 | $0.28 |
| Results tracked | 52 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 45.9 (#63), MiMo-V2.5: 43.6 (#75)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| SciCode | 35.7% | 43.1% |
| LMArena Coding | 1427 | 1469 |
| ALE-Bench | 804.12 | 513.95 |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1438 |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.4 (#68), MiMo-V2.5: —
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning MiMo-V2.5 leads
DeepSeek-R1: 18.7 (#253), MiMo-V2.5: 27.8 (#98)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| CritPt | 1.1% | 3.7% |
| LMArena Hard Prompts | 1415 | 1450 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.3 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 42.0 (#70), MiMo-V2.5: 35.4 (#145)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1401 | 1436 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| ProofBench | — | 16% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.3 (#81), MiMo-V2.5: 40.2 (#109)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1394 | 1459 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, MiMo-V2.5: 39.0 (#53)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Too close to call
DeepSeek-R1: 52.6 (#80), MiMo-V2.5: 52.0 (#96)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1412 | 1404 |
| LMArena Chinese | 1443 | 1467 |
| LMArena French | 1415 | 1447 |
| LMArena German | 1405 | 1421 |
| LMArena Japanese | 1394 | 1304 |
| LMArena Korean | 1359 | 1363 |
| LMArena Russian | 1423 | 1395 |
| LMArena Spanish | 1410 | 1412 |
Instruction Following MiMo-V2.5 leads
DeepSeek-R1: 72.2 (#138), MiMo-V2.5: 75.7 (#55)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1433 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), MiMo-V2.5: 44.1 (#69)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1391 | 1444 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Too close to call
DeepSeek-R1: 61.5 (#84), MiMo-V2.5: 61.8 (#82)
| Benchmark | DeepSeek-R1 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1428 | 1427 |
| LMArena Creative Writing | 1406 | 1392 |
| LMArena Multi-Turn | 1404 | 1445 |
| 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 MiMo-V2.5?
DeepSeek-R1 and MiMo-V2.5 score almost the same on the Noometry Index (42.0 vs 43.0), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-R1 or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or MiMo-V2.5 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-R1 and MiMo-V2.5 share?
20 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and MiMo-V2.5 has 23.