Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 37.0 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 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5 leads 43.6 to 31.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 37.0 | 43.0 |
| Released | 2024-09-06 | 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 | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), MiMo-V2.5: 43.6 (#75)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1310 | 1469 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 513.95 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), MiMo-V2.5: 27.8 (#98)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1450 |
| CritPt | — | 3.7% |
Math MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), MiMo-V2.5: 35.4 (#145)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1289 | 1436 |
| ProofBench | — | 16% |
Knowledge MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), MiMo-V2.5: 40.2 (#109)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1266 | 1459 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiMo-V2.5: 39.0 (#53)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), MiMo-V2.5: 52.0 (#96)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1273 | 1404 |
| LMArena Chinese | 1317 | 1467 |
| LMArena French | 1288 | 1447 |
| LMArena German | 1258 | 1421 |
| LMArena Japanese | 1228 | 1304 |
| LMArena Korean | 1209 | 1363 |
| LMArena Russian | 1289 | 1395 |
| LMArena Spanish | 1248 | 1412 |
Instruction Following MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), MiMo-V2.5: 75.7 (#55)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1433 |
Long Context MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), MiMo-V2.5: 44.1 (#69)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1301 | 1444 |
Writing & Preference MiMo-V2.5 leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), MiMo-V2.5: 61.8 (#82)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1294 | 1427 |
| LMArena Creative Writing | 1285 | 1392 |
| LMArena Multi-Turn | 1297 | 1445 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiMo-V2.5 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiMo-V2.5 has 23.