# Kimi K3 vs Qwen3.5 Max Preview

> Kimi K3 is the stronger model overall, scoring 59.5 to 45.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k3-vs-qwen3-5-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Qwen3.5 Max Preview in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 40.1.
- Kimi K3 has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 59.5 | 45.3 |
| Rank | 15 | 71 |
| Context | 1.05M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Open | Proprietary |

## Coding

- Kimi K3: 61.0 (#10)
- Qwen3.5 Max Preview: 44.0 (#77)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1508 | 1487 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |

## Agentic & Tool Use

- Kimi K3: 41.8 (#20)
- Qwen3.5 Max Preview: —

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| 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: 63.0 (#17)
- Qwen3.5 Max Preview: 30.8 (#84)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1483 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |

## Math

- Kimi K3: 74.2 (#16)
- Qwen3.5 Max Preview: 40.1 (#94)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1491 | 1474 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |

## Knowledge

- Kimi K3: 63.2 (#21)
- Qwen3.5 Max Preview: 41.8 (#107)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1521 | 1489 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |

## Multimodal

- Kimi K3: 37.8 (#70)
- Qwen3.5 Max Preview: —

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- Kimi K3: 56.3 (#21)
- Qwen3.5 Max Preview: 56.2 (#22)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1466 | 1465 |
| LMArena Chinese | 1529 | 1534 |
| LMArena French | 1491 | 1484 |
| LMArena German | 1488 | 1487 |
| LMArena Japanese | 1487 | 1495 |
| LMArena Korean | 1458 | 1438 |
| LMArena Russian | 1482 | 1471 |
| LMArena Spanish | 1472 | 1470 |

## Instruction Following

- Kimi K3: 77.7 (#14)
- Qwen3.5 Max Preview: 77.0 (#31)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1483 | 1467 |

## Long Context

- Kimi K3: 45.8 (#29)
- Qwen3.5 Max Preview: 45.2 (#45)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1494 | 1476 |

## Writing & Preference

- Kimi K3: 76.6 (#4)
- Qwen3.5 Max Preview: 66.0 (#41)

| Benchmark | Kimi K3 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1476 | 1470 |
| LMArena Creative Writing | 1454 | 1464 |
| LMArena Multi-Turn | 1488 | 1478 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |

## FAQ

### Is Kimi K3 better than Qwen3.5 Max Preview?

Kimi K3 is the stronger model overall, scoring 59.5 to 45.3 on the Noometry Index.

### Is Kimi K3 or Qwen3.5 Max Preview better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 44.0 in the Noometry coding category.

### How many benchmarks do Kimi K3 and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Qwen3.5 Max Preview has 17.