Model comparison
Kimi K2 (Jul 2025) vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 41.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 2 categories and MiMo-V2.5 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 36.8.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.
Side by side
| Kimi K2 (Jul 2025) | MiMo-V2.5 | |
|---|---|---|
| Provider | Moonshot AI | Xiaomi |
| Noometry Index | 41.2 | 43.4 |
| Released | 2025-07-12 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 262K | 1.05M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.57 | $0.14 |
| Output $ / M tokens | $2.30 | $0.28 |
| Results tracked | 42 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Kimi K2 (Jul 2025): 42.4 (#102), MiMo-V2.5: 43.9 (#81)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1399 | 1469 |
| ALE-Bench | 597.5 | 513.95 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), MiMo-V2.5: —
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning MiMo-V2.5 leads
Kimi K2 (Jul 2025): 23.3 (#179), MiMo-V2.5: 28.6 (#101)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1450 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| CritPt | — | 3.7% |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), MiMo-V2.5: 36.8 (#163)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1397 | 1436 |
| ProofBench | — | 16% |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge MiMo-V2.5 leads
Kimi K2 (Jul 2025): 37.3 (#157), MiMo-V2.5: 40.8 (#115)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1365 | 1460 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, MiMo-V2.5: 39.8 (#54)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual MiMo-V2.5 leads
Kimi K2 (Jul 2025): 49.6 (#130), MiMo-V2.5: 51.9 (#99)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1372 | 1404 |
| LMArena Chinese | 1415 | 1468 |
| LMArena French | 1379 | 1447 |
| LMArena German | 1387 | 1421 |
| LMArena Japanese | 1349 | 1306 |
| LMArena Korean | 1325 | 1363 |
| LMArena Russian | 1385 | 1395 |
| LMArena Spanish | 1386 | 1416 |
Instruction Following MiMo-V2.5 leads
Kimi K2 (Jul 2025): 71.1 (#156), MiMo-V2.5: 75.5 (#60)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1348 | 1434 |
| IFEval | 85% | — |
Long Context MiMo-V2.5 leads
Kimi K2 (Jul 2025): 41.2 (#145), MiMo-V2.5: 44.2 (#73)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1353 | 1445 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Too close to call
Kimi K2 (Jul 2025): 62.3 (#78), MiMo-V2.5: 61.6 (#86)
| Benchmark | Kimi K2 (Jul 2025) | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1380 | 1428 |
| LMArena Creative Writing | 1350 | 1393 |
| LMArena Multi-Turn | 1371 | 1445 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 41.2 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Kimi K2 (Jul 2025) or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K2 (Jul 2025) and MiMo-V2.5 share?
18 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and MiMo-V2.5 has 23.