# Granite 4.0 H Small vs Kimi K2 (Jul 2025)

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-kimi-k2
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Granite 4.0 H Small scores higher in 1 category and Kimi K2 (Jul 2025) in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.5 to 44.0.
- The biggest single-benchmark swing is Omni-MATH: 29.6% for Granite 4.0 H Small and 65.4% for Kimi K2 (Jul 2025).

## Snapshot

| | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 35.9 | 40.9 |
| Rank | 213 | 134 |
| Context | — | 262K |
| Input $/M | — | $0.57 |
| Output $/M | — | $2.30 |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Kimi K2 (Jul 2025): 43.1 (#83)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Coding | 1247 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| ALE-Bench | — | 597.5 |

## Agentic & Tool Use

- Granite 4.0 H Small: —
- Kimi K2 (Jul 2025): 32.2 (#59)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Kimi K2 (Jul 2025): 22.7 (#173)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1384 |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| Epoch Capabilities Index | — | 146.02 |
| ForecastBench | — | 60.2 |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Kimi K2 (Jul 2025): 40.1 (#81)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 29.6% | 65.4% |
| LMArena Math | 1251 | 1396 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Kimi K2 (Jul 2025): 36.9 (#153)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 56.9% | 81.9% |
| Vectara Hallucination Rate | 5.2% | 17.9% |
| GPQA (HELM) | 38.3% | 65.3% |
| LMArena Expert | 1244 | 1363 |
| Confabulations | — | 20.4% |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Kimi K2 (Jul 2025): 49.8 (#125)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1216 | 1372 |
| LMArena Chinese | 1250 | 1416 |
| LMArena Russian | 1198 | 1384 |
| LMArena Spanish | 1258 | 1383 |
| LMArena French | — | 1379 |
| LMArena German | — | 1386 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1324 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Kimi K2 (Jul 2025): 71.3 (#151)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 89% | 85% |
| LMArena Instruction Following | 1221 | 1347 |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Kimi K2 (Jul 2025): 41.2 (#140)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1240 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Kimi K2 (Jul 2025): 62.5 (#76)

| Benchmark | Granite 4.0 H Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1241 | 1380 |
| LMArena Creative Writing | 1210 | 1349 |
| WildBench | 73.9% | 86.2% |
| LMArena Multi-Turn | 1243 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |

## FAQ

### Is Granite 4.0 H Small better than Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 35.9 on the Noometry Index.

### Is Granite 4.0 H Small or Kimi K2 (Jul 2025) better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 35.8 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Kimi K2 (Jul 2025) share?

19 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Kimi K2 (Jul 2025) has 42.