# Kimi K2.5 vs Qwen Max

> Kimi K2.5 is the stronger model overall, scoring 48.1 to 34.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-5-vs-qwen-max
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 leads 51.8 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Kimi K2.5 and 16.1% for Qwen Max.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Kimi K2.5 accepts more context: 262K tokens versus 33K.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2.5 | Qwen Max |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 48.1 | 34.7 |
| Rank | 57 | 230 |
| Context | 262K | 33K |
| Input $/M | $0.45 | $1.60 |
| Output $/M | $2.25 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- Kimi K2.5: 48.8 (#53)
- Qwen Max: 30.7 (#292)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| LMArena Coding | 1474 | 1288 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |

## Agentic & Tool Use

- Kimi K2.5: 34.2 (#48)
- Qwen Max: —

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |

## Reasoning

- Kimi K2.5: 31.2 (#80)
- Qwen Max: 25.1 (#151)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1269 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| Epoch Capabilities Index | 148.03 | — |

## Math

- Kimi K2.5: 51.8 (#53)
- Qwen Max: 22.3 (#276)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 16.1% |
| LMArena Math | 1470 | 1275 |
| FrontierMath (Feb 2025 set) | 27.9% | 1% |
| MathArena Final-Answer Competitions | 62.3% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Kimi K2.5: 53.6 (#56)
- Qwen Max: 30.3 (#228)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| GPQA Diamond | 87.6% | 56.1% |
| LMArena Expert | 1466 | 1248 |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |

## Multimodal

- Kimi K2.5: 41.1 (#39)
- Qwen Max: —

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |

## Multilingual

- Kimi K2.5: 53.9 (#53)
- Qwen Max: 41.8 (#202)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1433 | 1263 |
| LMArena Chinese | 1495 | 1254 |
| LMArena French | 1454 | 1330 |
| LMArena German | 1441 | 1254 |
| LMArena Japanese | 1421 | 1205 |
| LMArena Korean | 1410 | 1142 |
| LMArena Russian | 1435 | 1274 |
| LMArena Spanish | 1450 | 1290 |

## Instruction Following

- Kimi K2.5: 75.3 (#64)
- Qwen Max: 66.5 (#208)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1431 | 1262 |

## Long Context

- Kimi K2.5: 52.1 (#7)
- Qwen Max: 39.4 (#180)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 86.1% | 66.7% |
| LMArena Longer Query | 1445 | 1288 |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |

## Writing & Preference

- Kimi K2.5: 65.1 (#53)
- Qwen Max: 47.8 (#205)

| Benchmark | Kimi K2.5 | Qwen Max |
|---|---|---|
| LMArena Text | 1445 | 1282 |
| LMArena Creative Writing | 1423 | 1248 |
| LMArena Multi-Turn | 1444 | 1277 |
| EQ-Bench Creative Writing | 1579 | — |

## FAQ

### Is Kimi K2.5 better than Qwen Max?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 34.7 on the Noometry Index.

### Which is cheaper, Kimi K2.5 or Qwen Max?

Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is Kimi K2.5 or Qwen Max better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.5 does, with 262K tokens against 33K.

### How many benchmarks do Kimi K2.5 and Qwen Max share?

21 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen Max has 23.