Model comparison
Grok 4.20 (Non-Reasoning) vs MiMo-V2.6-Pro
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 46.7 on the Noometry Index. MiMo-V2.6-Pro costs 2.9× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 3 categories and MiMo-V2.6-Pro in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 30.4.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 1M.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 48.5 | 46.7 |
| Released | 2026-02-17 | 2026-09-22 |
| Weights | Proprietary | Open |
| Context window | 1M | 1.05M |
| Max output | 30K | 131K |
| Input $ / M tokens | $1.25 | $0.43 |
| Output $ / M tokens | $2.50 | $0.87 |
| Results tracked | 46 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Grok 4.20 (Non-Reasoning): 41.8 (#104), MiMo-V2.6-Pro: 53.2 (#27)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1374 | 1618 |
| LMArena Coding | 1458 | 1538 |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.3 (#43), MiMo-V2.6-Pro: —
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.2 (#30), MiMo-V2.6-Pro: 30.4 (#76)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1511 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| Epoch Capabilities Index | 152.01 | — |
| ForecastBench | 61.4 | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.0 (#54), MiMo-V2.6-Pro: 37.9 (#91)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1455 | 1497 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#54), MiMo-V2.6-Pro: 43.0 (#85)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1440 | 1548 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
Multimodal MiMo-V2.6-Pro leads
Grok 4.20 (Non-Reasoning): 33.2 (#88), MiMo-V2.6-Pro: 40.2 (#40)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1263 | 1265 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual MiMo-V2.6-Pro leads
Grok 4.20 (Non-Reasoning): 54.7 (#38), MiMo-V2.6-Pro: 57.0 (#15)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1440 | 1474 |
| LMArena Chinese | 1481 | 1532 |
| LMArena Russian | 1457 | 1481 |
| LMArena French | 1477 | — |
| LMArena German | 1463 | — |
| LMArena Japanese | 1450 | — |
| LMArena Korean | 1417 | — |
| LMArena Spanish | 1442 | — |
Instruction Following MiMo-V2.6-Pro leads
Grok 4.20 (Non-Reasoning): 75.0 (#79), MiMo-V2.6-Pro: 78.2 (#10)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1420 | 1490 |
Long Context Too close to call
Grok 4.20 (Non-Reasoning): 45.4 (#33), MiMo-V2.6-Pro: 46.0 (#26)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1436 | 1500 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference MiMo-V2.6-Pro leads
Grok 4.20 (Non-Reasoning): 65.9 (#42), MiMo-V2.6-Pro: 66.9 (#32)
| Benchmark | Grok 4.20 (Non-Reasoning) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1451 | 1491 |
| LMArena Creative Writing | 1439 | 1465 |
| LMArena Multi-Turn | 1456 | 1463 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than MiMo-V2.6-Pro?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 46.7 on the Noometry Index. MiMo-V2.6-Pro costs 2.9× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) 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; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 41.8 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 Grok 4.20 (Non-Reasoning) and MiMo-V2.6-Pro share?
14 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and MiMo-V2.6-Pro has 14.