Model comparison
Kimi K3 vs MiMo-V2.5-Pro
Kimi K3 is the stronger model overall, scoring 59.5 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and MiMo-V2.5-Pro in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 26.8.
- The biggest single-benchmark swing is ProofBench: 87% for Kimi K3 and 22% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $3 / $15 for Kimi K3.
Side by side
| Kimi K3 | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Moonshot AI | Xiaomi |
| Noometry Index | 59.5 | 45.2 |
| Released | 2026-07-16 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 1.05M | 1.05M |
| Max output | 1.05M | 131K |
| Input $ / M tokens | $3 | $0.43 |
| Output $ / M tokens | $15 | $0.87 |
| Results tracked | 53 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1654 | 1479 |
| SciCode | 59.5% | 50.2% |
| LMArena Coding | 1508 | 1503 |
| ALE-Bench | 1,524 | 899.8 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| FrontierSWE | 25.9% | — |
| WeirdML | 82.6% | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), MiMo-V2.5-Pro: —
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 93.6% | 34.4% |
| CritPt | 23.4% | 4% |
| LMArena Hard Prompts | 1496 | 1488 |
| DTBench | 91.2% | 84.5% |
| LMCA | 52.7% | 29.5% |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 87% | 22% |
| LMArena Math | 1491 | 1481 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1521 | 1503 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
Multimodal Not comparable
Kimi K3: 37.8 (#70), MiMo-V2.5-Pro: —
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1466 | 1449 |
| LMArena Chinese | 1529 | 1507 |
| LMArena French | 1491 | 1488 |
| LMArena German | 1488 | 1458 |
| LMArena Japanese | 1487 | 1412 |
| LMArena Korean | 1458 | 1437 |
| LMArena Russian | 1482 | 1450 |
| LMArena Spanish | 1472 | 1471 |
Instruction Following Too close to call
Kimi K3: 77.7 (#14), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1483 | 1477 |
Long Context Too close to call
Kimi K3: 45.8 (#29), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1494 | 1483 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Kimi K3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1476 | 1465 |
| LMArena Creative Writing | 1454 | 1440 |
| EQ-Bench Creative Writing | 2082 | 1493 |
| EQ-Bench 4 | 1339 | 1208 |
| LMArena Multi-Turn | 1488 | 1477 |
Frequently asked questions
Is Kimi K3 better than MiMo-V2.5-Pro?
Kimi K3 is the stronger model overall, scoring 59.5 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or MiMo-V2.5-Pro better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 47.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Kimi K3 and MiMo-V2.5-Pro share?
27 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and MiMo-V2.5-Pro has 27.