# GPT-4 vs Kimi K2.5 Instant

> Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-kimi-k2-5-instant
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Kimi K2.5 Instant in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 Instant leads 36.6 to 10.1.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Noometry Index | 28.9 | 42.9 |
| Rank | 308 | 92 |
| Context | 8K | — |
| Input $/M | $30 | — |
| Output $/M | $60 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4: 31.2 (#277)
- Kimi K2.5 Instant: 42.3 (#95)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1254 | 1483 |
| LMArena WebDev | — | 1404 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- Kimi K2.5 Instant: —

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.3 (#285)
- Kimi K2.5 Instant: 28.5 (#88)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1443 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.88 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.1 (#304)
- Kimi K2.5 Instant: 36.6 (#105)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1269 | 1443 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#277)
- Kimi K2.5 Instant: 39.5 (#121)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1211 | 1438 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multimodal

- GPT-4: —
- Kimi K2.5 Instant: 39.5 (#47)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |

## Multilingual

- GPT-4: 40.8 (#210)
- Kimi K2.5 Instant: 52.2 (#89)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1246 | 1406 |
| LMArena Chinese | 1242 | 1450 |
| LMArena French | 1282 | 1403 |
| LMArena German | 1251 | 1413 |
| LMArena Korean | 1184 | 1378 |
| LMArena Russian | 1251 | 1404 |
| LMArena Spanish | 1261 | 1448 |
| LMArena Japanese | 1209 | — |

## Instruction Following

- GPT-4: 65.5 (#217)
- Kimi K2.5 Instant: 75.5 (#61)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1241 | 1430 |

## Long Context

- GPT-4: 37.7 (#207)
- Kimi K2.5 Instant: 43.8 (#82)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1244 | 1435 |

## Writing & Preference

- GPT-4: 35.0 (#263)
- Kimi K2.5 Instant: 60.8 (#91)

| Benchmark | GPT-4 | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1263 | 1420 |
| LMArena Creative Writing | 1244 | 1379 |
| LMArena Multi-Turn | 1257 | 1427 |
| EQ-Bench Creative Writing | 752 | — |

## FAQ

### Is GPT-4 better than Kimi K2.5 Instant?

Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 28.9 on the Noometry Index.

### Is GPT-4 or Kimi K2.5 Instant better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.3 versus 31.2 in the Noometry coding category.

### How many benchmarks do GPT-4 and Kimi K2.5 Instant share?

16 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Kimi K2.5 Instant has 18.