# GPT-4.5 vs Kimi K2.6

> Kimi K2.6 is the stronger model overall, scoring 47.5 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-kimi-k2-6
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Kimi K2.6 in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 31.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 96.1% for Kimi K2.6.
- Kimi K2.6 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 36.9 | 47.5 |
| Rank | 200 | 52 |
| Context | — | 262K |
| Input $/M | — | $0.95 |
| Output $/M | — | $4 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.5: 41.8 (#102)
- Kimi K2.6: 50.5 (#41)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| WeirdML | 39.4% | 55.9% |
| LMArena Coding | 1397 | 1488 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| LiveBench Coding | 75.2% | — |
| ALE-Bench | — | 1,093 |

## Agentic & Tool Use

- GPT-4.5: 27.6 (#92)
- Kimi K2.6: 21.8 (#128)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| Cybench | 17.5% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |

## Reasoning

- GPT-4.5: 14.1 (#320)
- Kimi K2.6: 39.6 (#51)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1470 |
| Epoch Capabilities Index | 136.74 | 151.03 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EnigmaEval | 3.2% | — |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 71.1% | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 37.3% |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 31.0 (#200)
- Kimi K2.6: 56.8 (#34)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 96.1% |
| LMArena Math | 1412 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- GPT-4.5: 32.4 (#205)
- Kimi K2.6: 53.9 (#48)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 68.7% | 90.8% |
| LMArena Expert | 1394 | 1491 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | — | 34.9% |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 10.8% |

## Multimodal

- GPT-4.5: 37.0 (#68)
- Kimi K2.6: 31.8 (#95)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1195 | 1282 |
| VPCT | 45% | — |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |

## Multilingual

- GPT-4.5: 52.7 (#78)
- Kimi K2.6: 55.1 (#35)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1413 | 1446 |
| LMArena Chinese | 1421 | 1521 |
| LMArena French | 1417 | 1471 |
| LMArena German | 1457 | 1449 |
| LMArena Japanese | 1416 | 1442 |
| LMArena Korean | 1392 | 1428 |
| LMArena Russian | 1419 | 1446 |
| LMArena Spanish | — | 1463 |

## Instruction Following

- GPT-4.5: 72.8 (#129)
- Kimi K2.6: 76.5 (#40)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1451 |
| LiveBench Instruction Following | 72.3% | — |

## Long Context

- GPT-4.5: 40.4 (#150)
- Kimi K2.6: 44.9 (#50)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1406 | 1468 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 57.1 (#129)
- Kimi K2.6: 68.7 (#25)

| Benchmark | GPT-4.5 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1417 | 1455 |
| LMArena Creative Writing | 1394 | 1434 |
| EQ-Bench Creative Writing | 1258 | 1725 |
| LMArena Multi-Turn | 1444 | 1453 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench 4 | — | 1202 |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.5 to 36.9 on the Noometry Index.

### Is GPT-4.5 or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 41.8 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and Kimi K2.6 share?

22 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Kimi K2.6 has 51.