Model comparison
DeepSeek V4 Pro vs MiMo-V2.6-Pro
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 50.3 on the Noometry Index. MiMo-V2.6-Pro costs 1.8× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 3 categories and MiMo-V2.6-Pro in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Pro leads 59.5 to 43.5.
- The biggest single-benchmark swing is ProofBench: 50% for DeepSeek V4 Pro and 70% for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 1M.
Side by side
| DeepSeek V4 Pro | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 54.3 | 50.3 |
| Released | 2026-04-24 | 2026-09-21 |
| Weights | Open | Open |
| Context window | 1M | 1.05M |
| Max output | 393K | 131K |
| Input $ / M tokens | $0.66 | $0.43 |
| Output $ / M tokens | $1.98 | $0.87 |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
DeepSeek V4 Pro: 52.4 (#34), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1582 | 1629 |
| SciCode | 51% | 60.9% |
| LMArena Coding | 1470 | 1534 |
| ALE-Bench | 1,403 | 1,158 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| WeirdML | 66.2% | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
DeepSeek V4 Pro: 32.8 (#58), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | 47.3% | 59.5% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 18% | 26.6% |
| LMArena Hard Prompts | 1461 | 1512 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 50% | 70% |
| LMArena Math | 1455 | 1494 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1464 | 1543 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multimodal Not comparable
DeepSeek V4 Pro: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
DeepSeek V4 Pro: 54.4 (#45), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1439 | 1474 |
| LMArena Chinese | 1486 | 1529 |
| LMArena Russian | 1453 | 1480 |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following MiMo-V2.6-Pro leads
DeepSeek V4 Pro: 76.1 (#47), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1448 | 1493 |
Long Context MiMo-V2.6-Pro leads
DeepSeek V4 Pro: 45.0 (#51), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1458 | 1501 |
| CL-bench Life | 13.5% | — |
Writing & Preference MiMo-V2.6-Pro leads
DeepSeek V4 Pro: 65.5 (#46), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | DeepSeek V4 Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1451 | 1492 |
| LMArena Creative Writing | 1446 | 1468 |
| LMArena Multi-Turn | 1467 | 1464 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than MiMo-V2.6-Pro?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 50.3 on the Noometry Index. MiMo-V2.6-Pro costs 1.8× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Pro or MiMo-V2.6-Pro?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.
Is DeepSeek V4 Pro or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 52.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4 Pro and MiMo-V2.6-Pro share?
18 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and MiMo-V2.6-Pro has 19.