# Granite 4.2 8B vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 47.8 to 40.0 on the Noometry Index. Granite 4.2 8B costs 8.4× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/granite-4-2-8b-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 0 categories and Kimi K2.5 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 37.7.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 131K.

## Snapshot

| | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 40.0 | 47.8 |
| Rank | 143 | 50 |
| Context | 131K | 262K |
| Input $/M | $0.06 | $0.45 |
| Output $/M | $0.25 | $2.25 |
| Weights | Open | Open |

## Coding

- Granite 4.2 8B: 39.9 (#138)
- Kimi K2.5: 48.7 (#48)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1379 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1436 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |

## Agentic & Tool Use

- Granite 4.2 8B: —
- Kimi K2.5: 34.0 (#44)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- Granite 4.2 8B: 25.5 (#130)
- Kimi K2.5: 31.2 (#74)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Hard Prompts | 1327 | 1454 |
| 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 | — | 148.05 |

## Math

- Granite 4.2 8B: —
- Kimi K2.5: 50.3 (#46)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| LMArena Math | — | 1470 |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Granite 4.2 8B: 37.7 (#144)
- Kimi K2.5: 53.6 (#52)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Expert | 1380 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Vectara Hallucination Rate | — | 14.2% |

## Multimodal

- Granite 4.2 8B: —
- Kimi K2.5: 40.4 (#37)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |

## Multilingual

- Granite 4.2 8B: 44.5 (#173)
- Kimi K2.5: 54.1 (#50)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1299 | 1433 |
| LMArena Chinese | 1361 | 1495 |
| LMArena Russian | 1283 | 1436 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1412 |
| LMArena Spanish | — | 1450 |

## Instruction Following

- Granite 4.2 8B: 68.7 (#183)
- Kimi K2.5: 75.5 (#60)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1298 | 1431 |

## Long Context

- Granite 4.2 8B: 40.2 (#154)
- Kimi K2.5: 52.1 (#7)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1323 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- Granite 4.2 8B: 49.8 (#183)
- Kimi K2.5: 65.3 (#51)

| Benchmark | Granite 4.2 8B | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1319 | 1445 |
| LMArena Creative Writing | 1238 | 1423 |
| LMArena Multi-Turn | 1299 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |

## FAQ

### Is Granite 4.2 8B better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 40.0 on the Noometry Index. Granite 4.2 8B costs 8.4× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.

### Which is cheaper, Granite 4.2 8B or Kimi K2.5?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.

### Is Granite 4.2 8B or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.5 does, with 262K tokens against 131K.

### How many benchmarks do Granite 4.2 8B and Kimi K2.5 share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Kimi K2.5 has 51.