Model comparison
DeepSeek-V3.2-Exp vs MiMo-V2-Flash
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 41.3 on the Noometry Index. MiMo-V2-Flash costs 1.7× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
DeepSeekSummary
- They share 20 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 7 categories and MiMo-V2-Flash in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 39.7.
- The biggest single-benchmark swing is SciCode: 38.9% for DeepSeek-V3.2-Exp and 25.9% for MiMo-V2-Flash.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- MiMo-V2-Flash accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.2-Exp | MiMo-V2-Flash | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 44.3 | 41.3 |
| Released | 2025-09-29 | 2025-12-16 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.26 | $0.14 |
| Output $ / M tokens | $0.38 | $0.28 |
| Results tracked | 49 | 21 |
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-Flash: 36.1 (#211)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena WebDev | 1362 | 1330 |
| SciCode | 38.9% | 25.9% |
| LMArena Coding | 1454 | 1443 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| WeirdML | 39.5% | — |
| ALE-Bench | — | 737.95 |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 32.7 (#59), MiMo-V2-Flash: —
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning MiMo-V2-Flash leads
DeepSeek-V3.2-Exp: 22.1 (#208), MiMo-V2-Flash: 24.9 (#157)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| CritPt | 2.9% | 0% |
| LMArena Hard Prompts | 1434 | 1420 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| 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-Flash: 38.3 (#139)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1435 | 1396 |
| 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-Flash: 39.7 (#131)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1436 | 1425 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), MiMo-V2-Flash: 51.0 (#113)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1409 | 1392 |
| LMArena Chinese | 1461 | 1462 |
| LMArena French | 1433 | 1429 |
| LMArena German | 1440 | 1395 |
| LMArena Japanese | 1374 | 1325 |
| LMArena Korean | 1371 | 1358 |
| LMArena Russian | 1424 | 1387 |
| LMArena Spanish | 1440 | 1420 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), MiMo-V2-Flash: 73.5 (#120)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1413 | 1392 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), MiMo-V2-Flash: 43.0 (#110)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1428 | 1409 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), MiMo-V2-Flash: 59.7 (#106)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1425 | 1411 |
| LMArena Creative Writing | 1403 | 1375 |
| LMArena Multi-Turn | 1427 | 1404 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than MiMo-V2-Flash?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 41.3 on the Noometry Index. MiMo-V2-Flash costs 1.7× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Exp or MiMo-V2-Flash?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is DeepSeek-V3.2-Exp or MiMo-V2-Flash better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Flash does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and MiMo-V2-Flash share?
20 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and MiMo-V2-Flash has 21.