Model comparison
DeepSeek-V3.2-Exp vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 44.3 on the Noometry Index. DeepSeek-V3.2-Exp costs 1.9× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 2 categories and MiMo-V2.6-Pro in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 22.1.
- The biggest single-benchmark swing is ProofBench: 8% for DeepSeek-V3.2-Exp and 70% for MiMo-V2.6-Pro.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-V3.2-Exp | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 44.3 | 50.3 |
| Released | 2025-09-29 | 2026-09-21 |
| Weights | Open | Open |
| 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 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 46.5 (#65), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1362 | 1629 |
| SciCode | 38.9% | 60.9% |
| LMArena Coding | 1454 | 1534 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| WeirdML | 39.5% | — |
| ALE-Bench | — | 1,158 |
Agentic & Tool Use MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 32.7 (#59), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | 21.3% | 59.5% |
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 22.1 (#208), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 2.9% | 26.6% |
| LMArena Hard Prompts | 1434 | 1512 |
| 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 MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 41.7 (#87), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 8% | 70% |
| LMArena Math | 1435 | 1494 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| 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-V2.6-Pro: 43.5 (#92)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1436 | 1543 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 52.2 (#90), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1409 | 1474 |
| LMArena Chinese | 1461 | 1529 |
| LMArena Russian | 1424 | 1480 |
| LMArena French | 1433 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1371 | — |
| LMArena Spanish | 1440 | — |
Instruction Following MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 74.5 (#93), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1413 | 1493 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1428 | 1501 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference MiMo-V2.6-Pro leads
DeepSeek-V3.2-Exp: 62.4 (#77), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | DeepSeek-V3.2-Exp | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1425 | 1492 |
| LMArena Creative Writing | 1403 | 1468 |
| LMArena Multi-Turn | 1427 | 1464 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 44.3 on the Noometry Index. DeepSeek-V3.2-Exp costs 1.9× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Exp or MiMo-V2.6-Pro?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is DeepSeek-V3.2-Exp or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 46.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and MiMo-V2.6-Pro share?
17 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and MiMo-V2.6-Pro has 19.