# Kimi K2.5 Instant vs Kimi K3

> Kimi K3 is the stronger model overall, scoring 59.5 to 42.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-5-instant-vs-kimi-k3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 1 category and Kimi K3 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.0 to 36.6.

## Snapshot

| | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| Provider | Moonshot AI | Moonshot AI |
| Noometry Index | 42.9 | 59.5 |
| Rank | 92 | 12 |
| Context | — | 1.05M |
| Input $/M | — | $3 |
| Output $/M | — | $15 |
| Weights | Open | Open |

## Coding

- Kimi K2.5 Instant: 42.3 (#95)
- Kimi K3: 60.6 (#8)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1404 | 1659 |
| LMArena Coding | 1483 | 1509 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| ALE-Bench | — | 1,524 |

## Agentic & Tool Use

- Kimi K2.5 Instant: —
- Kimi K3: 41.8 (#19)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |

## Reasoning

- Kimi K2.5 Instant: 28.5 (#88)
- Kimi K3: 63.0 (#15)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1495 |
| 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 | — | 157.68 |
| ForecastBench | — | 61.1 |

## Math

- Kimi K2.5 Instant: 36.6 (#105)
- Kimi K3: 74.0 (#13)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Math | 1443 | 1493 |
| 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 K2.5 Instant: 39.5 (#121)
- Kimi K3: 63.2 (#19)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Expert | 1438 | 1520 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |

## Multimodal

- Kimi K2.5 Instant: 39.5 (#47)
- Kimi K3: 38.4 (#58)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Vision | 1254 | — |
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |

## Multilingual

- Kimi K2.5 Instant: 52.2 (#89)
- Kimi K3: 56.5 (#20)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1406 | 1466 |
| LMArena Chinese | 1450 | 1528 |
| LMArena French | 1403 | 1488 |
| LMArena German | 1413 | 1474 |
| LMArena Korean | 1378 | 1465 |
| LMArena Russian | 1404 | 1481 |
| LMArena Spanish | 1448 | 1478 |
| LMArena Japanese | — | 1492 |

## Instruction Following

- Kimi K2.5 Instant: 75.5 (#61)
- Kimi K3: 77.8 (#13)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1430 | 1481 |

## Long Context

- Kimi K2.5 Instant: 43.8 (#82)
- Kimi K3: 45.8 (#27)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1435 | 1494 |

## Writing & Preference

- Kimi K2.5 Instant: 60.8 (#91)
- Kimi K3: 76.7 (#4)

| Benchmark | Kimi K2.5 Instant | Kimi K3 |
|---|---|---|
| LMArena Text | 1420 | 1476 |
| LMArena Creative Writing | 1379 | 1452 |
| LMArena Multi-Turn | 1427 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |

## FAQ

### Is Kimi K2.5 Instant better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 42.9 on the Noometry Index.

### Is Kimi K2.5 Instant or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 60.6 versus 42.3 in the Noometry coding category.

### How many benchmarks do Kimi K2.5 Instant and Kimi K3 share?

17 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Kimi K3 has 53.
