Model comparison
DeepSeek-V3.1-Terminus vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 43.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and MiMo-V2.6-Pro in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 26.4.
- The biggest single-benchmark swing is CritPt: 1.7% for DeepSeek-V3.1-Terminus and 26.6% for MiMo-V2.6-Pro.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 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-V3.1-Terminus | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 43.1 | 50.3 |
| Released | 2025-09-22 | 2026-09-21 |
| Weights | Open | Open |
| Context window | 164K | 1.05M |
| Max output | 147K | 131K |
| Input $ / M tokens | $0.27 | $0.43 |
| Output $ / M tokens | $1 | $0.87 |
| Results tracked | 16 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 42.0 (#113), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| SciCode | 40.6% | 60.9% |
| LMArena Coding | 1426 | 1534 |
| ALE-Bench | 745.17 | 1,158 |
| LMArena WebDev | — | 1629 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
Reasoning MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 26.4 (#133), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 1.7% | 26.6% |
| LMArena Hard Prompts | 1426 | 1512 |
| Kagi LLM Benchmark | 57.4% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 38.5 (#137), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1402 | 1494 |
| ProofBench | — | 70% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | — | 1543 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 52.1 (#92), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1407 | 1474 |
| LMArena Russian | 1436 | 1480 |
| LMArena Chinese | — | 1529 |
Instruction Following MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 74.0 (#106), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1404 | 1493 |
Long Context MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 43.4 (#97), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1421 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
DeepSeek-V3.1-Terminus: 61.0 (#92), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1419 | 1492 |
| LMArena Creative Writing | 1403 | 1468 |
| LMArena Multi-Turn | 1411 | 1464 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 43.1 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or MiMo-V2.6-Pro?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is DeepSeek-V3.1-Terminus or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 42.0 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-V3.1-Terminus and MiMo-V2.6-Pro share?
13 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and MiMo-V2.6-Pro has 19.