# Granite 4.2 30B vs Pokee-Isaac 28B

> Side-by-side benchmark comparison for Granite 4.2 30B and Pokee-Isaac 28B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/granite-4-2-30b-vs-pokee-isaac-28b
- Last updated: September 10, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Granite 4.2 30B if you want the stronger benchmark profile. Pokee-Isaac 28B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Granite 4.2 30B leads overall 50 to 46.
- The clearest category separation is in reasoning, where the averages are 54.7 for Granite 4.2 30B and 38.6 for Pokee-Isaac 28B.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 29.2% and 65.1%.
- Granite 4.2 30B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Pokee-Isaac 28B also has the larger context window at 10M.

## Model Snapshot

| Property | Granite 4.2 30B | Pokee-Isaac 28B |
|----------|----------|----------|
| Creator | IBM | Pokee AI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 10M |
| Overall Score | null | null |
| Benchmarks Covered | 14 | 7 |
| Pricing (input/output) | $0.00 / $0.00 | $0.15 / $1.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Pokee-Isaac 28B public-lane score: 49.2 (Estimated · #60/152)

| Benchmark | Granite 4.2 30B | Pokee-Isaac 28B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 29.2% | 65.1% | Pokee-Isaac 28B |
| τ³-bench results | 62.0% | 66.2% | Pokee-Isaac 28B |
| BFCL v4 | 61.4% | 70.9% | Pokee-Isaac 28B |
| MCP-Atlas claim coverage | Coming soon | 74.6% | Coming soon |
| PinchBench | Coming soon | 95.7% | Coming soon |

### Coding

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Pokee-Isaac 28B public-lane score: Coming soon

| Benchmark | Granite 4.2 30B | Pokee-Isaac 28B | Winner |
|-----------|-----------|-----------|--------|
| SWE Multilingual | 41.9% | Coming soon | Coming soon |
| SWE-bench Pro | 33.3% | Coming soon | Coming soon |
| SWE-bench Verified | 57% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 29.2% | 65.1% | Pokee-Isaac 28B |
| LiveCodeBench v6 | 75.8% | Coming soon | Coming soon |
| SciCode | 38.8% | Coming soon | Coming soon |

### Reasoning

- Winner: Coming soon
- Granite 4.2 30B public-lane score: 54.7 (Unranked · 2 rankable rows)
- Pokee-Isaac 28B public-lane score: 38.6 (Unranked · 1 rankable row)

| Benchmark | Granite 4.2 30B | Pokee-Isaac 28B | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | Coming soon | 60.7% | Coming soon |

### Knowledge

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Pokee-Isaac 28B public-lane score: Coming soon

| Benchmark | Granite 4.2 30B | Pokee-Isaac 28B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 66.4% | Coming soon | Coming soon |
| MMLU-Pro | 77.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Pokee-Isaac 28B public-lane score: Coming soon

| Benchmark | Granite 4.2 30B | Pokee-Isaac 28B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 77.2% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- Granite 4.2 30B public-lane score: Coming soon
- Pokee-Isaac 28B public-lane score: Coming soon

| Benchmark | Granite 4.2 30B | Pokee-Isaac 28B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 89.2% | Coming soon | Coming soon |
| HMMT Feb 2025 | 89.2% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Granite 4.2 30B or Pokee-Isaac 28B?

Granite 4.2 30B is ahead overall on BenchLM right now.

### Where is the biggest gap between Granite 4.2 30B and Pokee-Isaac 28B?

The widest category gap is in reasoning, where the averages are 54.7 for Granite 4.2 30B and 38.6 for Pokee-Isaac 28B.

### 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 Pokee-Isaac 28B cover on BenchLM?

Pokee-Isaac 28B currently has 7 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)
- [Pokee-Isaac 28B vs Granite 4.2 8B](/compare/granite-4-2-8b-vs-pokee-isaac-28b)
- [Granite 4.2 30B vs Granite 4.2 3B](/compare/granite-4-2-30b-vs-granite-4-2-3b)
- [Pokee-Isaac 28B vs Granite 4.2 3B](/compare/granite-4-2-3b-vs-pokee-isaac-28b)

## Explore More

- [Granite 4.2 30B profile](/models/granite-4-2-30b)
- [Pokee-Isaac 28B profile](/models/pokee-isaac-28b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)