IBM Models: Intelligence, Performance & Price
Artificial Analysis Intelligence Index
* Estimated
Granite 4.2 3BGranite 4.2 30BGranite 4.2 8BGranite 4.0 H SmallGranite 4.0 MicroOutput speed
Per Intelligence Index Task
Artificial Analysis has benchmarked 13 models from IBM. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from IBM is Granite 4.2 30B at 15 (estimated).
- For output speed, the fastest model is Granite 4.2 3B at 216 t/s.
- For latency, Granite 4.2 3B at 9.77s offers the lowest time to first answer token.
- For pricing, Granite 4.2 3B at $0.01 offers the lowest cost per task. Prices vary up to 3.9x across models.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
All IBM Releases
Granite 4.2 30B
1 model
15
Highest Intelligence
Granite 4.2 3B
1 model
9
Highest Intelligence
Granite 4.2 8B
1 model
11
Highest Intelligence
Granite 4.1 30B
1 model
7
Highest Intelligence
Granite 4.1 3B
1 model
6
Highest Intelligence
Granite 4.1 8B
1 model
7
Highest Intelligence
Granite 4.0 350M
1 model
5
Highest Intelligence
Granite 4.0 H 350M
1 model
5
Highest Intelligence
Granite 4.0 H 1B
1 model
5
Highest Intelligence
Granite 4.0 1B
1 model
5
Highest Intelligence
Granite 4.0 H Small
1 model
6
Highest Intelligence
Granite 4.0 Micro
1 model
5
Highest Intelligence
Granite 3.3 8B
1 model
5
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Granite 4.2 30B | IBM | 15 | 30B | 131k | $0.1 | 77 |  | ||
| Granite 4.2 8B | IBM | 11 | 8B | 131k | $0.0 | 76 |  | ||
| Granite 4.2 3B | IBM | 9 | 3B | 131k | $0.0 | 216 | | ||
| Granite 4.1 30B | IBM | 7 | 30B | 131k | - | - | - | ||
| Granite 4.1 8B | IBM | 7 | 8B | 131k | $0.1 | 126 | | ||
| Granite 4.0 H Small | IBM | 6 | 32B 9B active at inference time | 128k | $0.1 | 15 |  | ||
| Granite 4.1 3B | IBM | 6 | 3B | 131k | - | - | - | ||
| Granite 4.0 H 1B | IBM | 5 | 1.5B | 128k | - | - | - | ||
| Granite 4.0 Micro | IBM | 5 | 3B | 128k | - | - | - | ||
| Granite 4.0 1B | IBM | 5 | 1.6B | 128k | - | - | - | ||
| Granite 3.3 8B (Non-reasoning) | IBM | 5 | 8.2B | 128k | $0.1 | 15 | | ||
| Granite 4.0 350M | IBM | 5 | 0.3B | 33k | - | - | - | ||
| Granite 4.0 H 350M | IBM | 5 | 0.3B | 33k | - | - | - |