Model comparison
DeepSeek-V3.2-Exp vs MiMo-V2-Pro
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 43.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 4 categories and MiMo-V2-Pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 41.4.
- The biggest single-benchmark swing is Thematic Generalization: 65% for DeepSeek-V3.2-Exp and 45.9% for MiMo-V2-Pro.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | MiMo-V2-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 44.3 | 43.0 |
| Released | 2025-09-29 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.26 | $0.43 |
| Output $ / M tokens | $0.38 | $0.87 |
| Results tracked | 49 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.5 (#65), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1362 | 1433 |
| LMArena Coding | 1454 | 1476 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
| ALE-Bench | — | 785.17 |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 32.7 (#59), MiMo-V2-Pro: —
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning Too close to call
DeepSeek-V3.2-Exp: 22.1 (#208), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 36.7% | 25.8% |
| Thematic Generalization | 65% | 45.9% |
| LMArena Hard Prompts | 1434 | 1457 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1435 | 1447 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1436 | 1478 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual Too close to call
DeepSeek-V3.2-Exp: 52.2 (#90), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1409 | 1416 |
| LMArena Chinese | 1461 | 1456 |
| LMArena French | 1433 | 1469 |
| LMArena German | 1440 | 1417 |
| LMArena Japanese | 1374 | 1366 |
| LMArena Korean | 1371 | 1400 |
| LMArena Russian | 1424 | 1427 |
| LMArena Spanish | 1440 | 1457 |
Instruction Following MiMo-V2-Pro leads
DeepSeek-V3.2-Exp: 74.5 (#93), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1413 | 1445 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| CL-bench | 13.2% | 15.7% |
| CL-bench Life | 9.5% | 6.9% |
| LMArena Longer Query | 1428 | 1455 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Too close to call
DeepSeek-V3.2-Exp: 62.4 (#77), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1425 | 1436 |
| LMArena Creative Writing | 1403 | 1415 |
| LMArena Multi-Turn | 1427 | 1456 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than MiMo-V2-Pro?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 43.0 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or MiMo-V2-Pro?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is DeepSeek-V3.2-Exp or MiMo-V2-Pro better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 43.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and MiMo-V2-Pro share?
22 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and MiMo-V2-Pro has 23.