# Granite 4.2 30B vs Kimi K2.5

> Side-by-side benchmark comparison for Granite 4.2 30B and Kimi K2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/granite-4-2-30b-vs-kimi-k2-5
- Last updated: September 10, 2026

- Shared sourced benchmarks: 10
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Kimi K2.5 if you want the stronger benchmark profile. Granite 4.2 30B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Kimi K2.5 leads overall 54.01 to 50.
- The clearest category separation is in reasoning, where the averages are 54.7 for Granite 4.2 30B and 54.1 for Kimi K2.5.
- The biggest single benchmark swing is SWE Multilingual in Coding, with scores of 41.9% and 73%.
- Granite 4.2 30B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Kimi K2.5 also has the larger context window at 256K.

## Model Snapshot

| Property | Granite 4.2 30B | Kimi K2.5 |
|----------|----------|----------|
| Creator | IBM | Moonshot AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 128K | 256K |
| Overall Score | null | 54.01 |
| Benchmarks Covered | 14 | 45 |
| Pricing (input/output) | $0.00 / $0.00 | $0.60 / $3.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 46.4 (Estimated · #77/152)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 29.2% | Coming soon | Coming soon |
| τ³-bench results | 62.0% | 65.7% | Kimi K2.5 |
| BFCL v4 | 61.4% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 50.8% | Coming soon |
| BrowseComp | Coming soon | 60.6% | Coming soon |
| Claw-Eval | Coming soon | 52.3% | Coming soon |
| QwenClawBench | Coming soon | 54.3% | Coming soon |
| DeepSearchQA | Coming soon | 77.1% | Coming soon |
| DeepPlanning | Coming soon | 14.4% | Coming soon |
| Toolathlon | Coming soon | 27.8% | Coming soon |
| MCP Atlas | Coming soon | 29.5% | Coming soon |
| MCP-Tasks | Coming soon | 59.1% | Coming soon |
| WideResearch | Coming soon | 72.7% | Coming soon |
| Gert Labs | Coming soon | 45.88% | Coming soon |
| ResearchClawBench | Coming soon | 14.0% | Coming soon |
| JobBench | Coming soon | 8.7% | Coming soon |

### Coding

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 50.6 (Estimated · #55/151)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE Multilingual | 41.9% | 73% | Kimi K2.5 |
| SWE-bench Pro | 33.3% | 50.7% | Kimi K2.5 |
| SWE-bench Verified | 57% | 76.8% | Kimi K2.5 |
| Terminal-Bench 2.1 | 29.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | 75.8% | 85.0% | Kimi K2.5 |
| SciCode | 38.8% | 48.7% | Kimi K2.5 |
| SWE-bench Verified* | Coming soon | 70.8% | Coming soon |
| SWE-Rebench | Coming soon | 58.5% | Coming soon |
| React Native Evals | Coming soon | 77.2% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 65.7 (#24/48)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 78.5% | Coming soon |
| Video-MME | Coming soon | 87.4% | Coming soon |
| MMVU | Coming soon | 80.4% | Coming soon |
| VideoMMMU | Coming soon | 86.6% | Coming soon |

### Reasoning

- Winner: Coming soon
- Granite 4.2 30B public-lane score: 54.7 (Unranked · 2 rankable rows)
- Kimi K2.5 public-lane score: 54.1 (Unranked · 3 rankable rows)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 61% | Coming soon |

### Knowledge

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 52 (Estimated · #69/183)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 66.4% | 87.6% | Kimi K2.5 |
| MMLU-Pro | 77.6% | 87.1% | Kimi K2.5 |
| GPQA-D | Coming soon | 87.6% | Coming soon |
| SuperGPQA | Coming soon | 69.2% | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 87.1% | Coming soon |
| HLE | Coming soon | 30.1% | Coming soon |

### Instruction Following

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 85.8 (#41/123)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 77.2% | Coming soon | Coming soon |
| IFEval | Coming soon | 93.9% | Coming soon |

### Multilingual

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 38.2 (#8/12)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 82.3% | Coming soon |
| NOVA-63 | Coming soon | 56.0% | Coming soon |

### Mathematics

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Kimi K2.5 public-lane score: 62.4 (#5/7)

| Benchmark | Granite 4.2 30B | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 89.2% | 96.1% | Kimi K2.5 |
| HMMT Feb 2025 | 89.2% | 95.4% | Kimi K2.5 |
| AIME26 | Coming soon | 95.8% | Coming soon |
| AIME25 (Arcee) | Coming soon | 96.3% | Coming soon |
| HMMT Nov 2025 | Coming soon | 91.1% | Coming soon |
| HMMT Feb 2026 | Coming soon | 87.1% | Coming soon |
| MMAnswerBench | Coming soon | 81.8% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 27.900% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 4.200% | Coming soon |

## FAQ

### Which is better overall, Granite 4.2 30B or Kimi K2.5?

Kimi K2.5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Granite 4.2 30B and Kimi K2.5?

The widest category gap is in reasoning, where the averages are 54.7 for Granite 4.2 30B and 54.1 for Kimi K2.5.

### How many benchmarks does Granite 4.2 30B cover on BenchLM?

Granite 4.2 30B currently has 14 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K2.5 cover on BenchLM?

Kimi K2.5 currently has 45 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Granite 4.2 30B vs Granite 4.2 8B](/compare/granite-4-2-30b-vs-granite-4-2-8b)
- [Kimi K2.5 vs Granite 4.2 8B](/compare/granite-4-2-8b-vs-kimi-k2-5)
- [Granite 4.2 30B vs Granite 4.2 3B](/compare/granite-4-2-30b-vs-granite-4-2-3b)
- [Kimi K2.5 vs Granite 4.2 3B](/compare/granite-4-2-3b-vs-kimi-k2-5)

## Explore More

- [Granite 4.2 30B profile](/models/granite-4-2-30b)
- [Kimi K2.5 profile](/models/kimi-k2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)