Granite 4.2 30B
By IBM · released 2026-08-25 (1 month) · snapshot 2026-10-24
- Intelligence index
- 12.70
- Cost to run the AA index
- $111
- Price per 1M tokens (in / out)
- $0.16 / $0.65
- End-to-end time
- 36.1s
Is Granite 4.2 30B on the Pareto frontier, and what beats it?
Off the frontier
No. MiMo-V2.6-Flash is at least as smart for the same money or less.
Next step up: GPT-6 Luna (Max), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Granite 4.2 30B | IBM | 12.70 | $111 | 36.1s | 2026-08-25 | ||
| 2 | MiMo-V2.6-Flash | Xiaomi | 37.90 | $110 | 49.5s | 2026-09-21 | Frontier | |
| 3 | GPT-6 Luna (Max) | OpenAI | 38.10 | $122 | 82.0s | 2026-09-22 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Granite 4.2 30B today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: granite-4-2-30b.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- Granite 4.2 30B vs MiMo-V2.6-Flash
- Granite 4.2 30B vs GPT-6 Luna (Max)
- Granite 4.2 30B vs GPT-6 Luna (High)
- Granite 4.2 30B vs Claude Haiku 5.5 (Medium)
- Granite 4.2 30B vs GPT-6 Luna (Xhigh)
- Granite 4.2 30B vs Claude Haiku 5.5 (High)
- Granite 4.2 30B vs Claude Haiku 5.5 (Xhigh)
- Granite 4.2 30B vs MiMo-V2.6-Pro
What the Granite 4.2 30B release did to the frontier on 2026-08-25
None of its 1 effort levels reached the frontier at launch.
Closest miss: Granite 4.2 30B, 2.8 points below GPT-5.6 Luna (Non-reasoning) at 4.8× the cost.
Should you use Granite 4.2 30B?
Should you use Granite 4.2 30B?
Only when it fits your setup: MiMo-V2.6-Flash is at least as smart for the same money or less, so Granite 4.2 30B is off the value frontier today.
What is better and cheaper than Granite 4.2 30B?
MiMo-V2.6-Flash — at least as smart for the same money or less.
How much does Granite 4.2 30B cost?
$0.16/$0.65 in/out per 1M tokens, and $111 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Granite 4.2 30B on the Pareto frontier?
No: MiMo-V2.6-Flash beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Granite 4.2 30B is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/granite-4-2-30b · Markdown: /api/v1/models/granite-4-2-30b?format=md · llms.txt · agent skill