Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and MiMo-V2-Pro in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 49.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 37.6 | 43.0 |
| Released | 2024-09-06 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1309 | 1476 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1433 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 785.17 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
Math MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1288 | 1447 |
Knowledge MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1266 | 1478 |
Multilingual MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1273 | 1416 |
| LMArena Chinese | 1318 | 1456 |
| LMArena French | 1289 | 1469 |
| LMArena German | 1258 | 1417 |
| LMArena Japanese | 1228 | 1366 |
| LMArena Korean | 1209 | 1400 |
| LMArena Russian | 1289 | 1427 |
| LMArena Spanish | 1248 | 1457 |
Instruction Following MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1280 | 1445 |
Long Context MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1301 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1294 | 1436 |
| LMArena Creative Writing | 1285 | 1415 |
| LMArena Multi-Turn | 1297 | 1456 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiMo-V2-Pro share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiMo-V2-Pro has 23.