# Kimi K2 (Jul 2025) vs Qwen Max

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 34.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 22.3.
- The biggest single-benchmark swing is Aider Polyglot: 59.1% for Kimi K2 (Jul 2025) and 21.8% for Qwen Max.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 33K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 34.7 |
| Rank | 140 | 230 |
| Context | 262K | 33K |
| Input $/M | $0.57 | $1.60 |
| Output $/M | $2.30 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- Kimi K2 (Jul 2025): 42.4 (#102)
- Qwen Max: 30.7 (#292)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| Aider Polyglot | 59.1% | 21.8% |
| LMArena Coding | 1399 | 1288 |
| SWE-bench Verified (bash only) | 63.4% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |

## Agentic & Tool Use

- Kimi K2 (Jul 2025): 32.4 (#64)
- Qwen Max: —

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 23.3 (#179)
- Qwen Max: 25.1 (#151)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1269 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |

## Math

- Kimi K2 (Jul 2025): 42.7 (#83)
- Qwen Max: 22.3 (#276)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| LMArena Math | 1397 | 1275 |
| FrontierMath (Feb 2025 set) | 21.4% | 1% |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| Omni-MATH | 65.4% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 37.3 (#157)
- Qwen Max: 30.3 (#228)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| LMArena Expert | 1365 | 1248 |
| GPQA Diamond | — | 56.1% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |

## Multilingual

- Kimi K2 (Jul 2025): 49.6 (#130)
- Qwen Max: 41.8 (#202)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| LMArena Non-English | 1372 | 1263 |
| LMArena Chinese | 1415 | 1254 |
| LMArena French | 1379 | 1330 |
| LMArena German | 1387 | 1254 |
| LMArena Japanese | 1349 | 1205 |
| LMArena Korean | 1325 | 1142 |
| LMArena Russian | 1385 | 1274 |
| LMArena Spanish | 1386 | 1290 |

## Instruction Following

- Kimi K2 (Jul 2025): 71.1 (#156)
- Qwen Max: 66.5 (#208)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1348 | 1262 |
| IFEval | 85% | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#145)
- Qwen Max: 39.4 (#180)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 66.7% | 66.7% |
| LMArena Longer Query | 1353 | 1288 |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.3 (#78)
- Qwen Max: 47.8 (#205)

| Benchmark | Kimi K2 (Jul 2025) | Qwen Max |
|---|---|---|
| LMArena Text | 1380 | 1282 |
| LMArena Creative Writing | 1350 | 1248 |
| LMArena Multi-Turn | 1371 | 1277 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Qwen Max?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 34.7 on the Noometry Index.

### Which is cheaper, Kimi K2 (Jul 2025) or Qwen Max?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is Kimi K2 (Jul 2025) or Qwen Max better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 33K.

### How many benchmarks do Kimi K2 (Jul 2025) and Qwen Max share?

20 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen Max has 23.