Model comparison
DeepSeek LLM 67B vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2.5 leads 40.8 to 7.0.
Side by side
| DeepSeek LLM 67B | MiMo-V2.5 | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 24.9 | 43.4 |
| Released | 2023-11-29 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 15 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
DeepSeek LLM 67B: 31.9 (#278), MiMo-V2.5: 43.9 (#81)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1096 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| ALE-Bench | — | 513.95 |
Reasoning MiMo-V2.5 leads
DeepSeek LLM 67B: 16.5 (#304), MiMo-V2.5: 28.6 (#101)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1450 |
| CritPt | — | 3.7% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math MiMo-V2.5 leads
DeepSeek LLM 67B: 8.7 (#324), MiMo-V2.5: 36.8 (#163)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1108 | 1436 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| ProofBench | — | 16% |
| MATH Level 5 | 6.4% | — |
Knowledge MiMo-V2.5 leads
DeepSeek LLM 67B: 7.0 (#313), MiMo-V2.5: 40.8 (#115)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1460 |
Multimodal Not comparable
DeepSeek LLM 67B: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual MiMo-V2.5 leads
DeepSeek LLM 67B: 29.4 (#267), MiMo-V2.5: 51.9 (#99)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1073 | 1404 |
| LMArena Chinese | 1132 | 1468 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1416 |
Instruction Following MiMo-V2.5 leads
DeepSeek LLM 67B: 55.4 (#277), MiMo-V2.5: 75.5 (#60)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1434 |
Long Context MiMo-V2.5 leads
DeepSeek LLM 67B: 33.1 (#265), MiMo-V2.5: 44.2 (#73)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1092 | 1445 |
Writing & Preference MiMo-V2.5 leads
DeepSeek LLM 67B: 31.6 (#282), MiMo-V2.5: 61.6 (#86)
| Benchmark | DeepSeek LLM 67B | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1105 | 1428 |
| LMArena Creative Writing | 1067 | 1393 |
| LMArena Multi-Turn | 1082 | 1445 |
Frequently asked questions
Is DeepSeek LLM 67B better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and MiMo-V2.5 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and MiMo-V2.5 has 23.