IBM Models: Intelligence, Performance & Price
Artificial Analysis Intelligence Index
Per Intelligence Index Task
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 8B at 5.
- For speed, Granite 4.2 8B at 8.7 min has the lowest time per task.
- For latency, Granite 4.2 8B at 38.63s offers the lowest time to first answer token.
- For pricing, Granite 4.2 8B at $0.04 offers the lowest cost per task.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Time per Intelligence Index Task
Capability Scores
Capability Indexes
Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better
Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better
Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better
All IBM Releases
Granite 4.2 30B
1 model
Granite 4.2 3B
1 model
5
Highest Intelligence
Granite 4.2 8B
1 model
5
Highest Intelligence
Granite 4.1 30B
1 model
Granite 4.1 3B
1 model
Granite 4.1 8B
1 model
Granite 4.0 350M
1 model
Granite 4.0 H 350M
1 model
Granite 4.0 H 1B
1 model
Granite 4.0 1B
1 model
Granite 4.0 H Small
1 model
Granite 4.0 Micro
1 model
Granite 3.3 8B
1 model
Further details
Weights | Provider Benchmarks | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Granite 4.2 8B | IBM | 5 | 8B | 131k | $0.0475 | 8.7 | 99 |   | ||
| Granite 4.2 3B | IBM | 5 | 3B | 131k | - | - | - | - | ||
| Granite 4.2 30B | IBM | - | 30B | 131k | - | - | - | - | ||
| Granite 4.0 Micro | IBM | - | 3B | 128k | - | - | - | - | ||
| Granite 3.3 8B (Non-reasoning) | IBM | - | 8.2B | 128k | - | - | - | - | ||
| Granite 4.0 350M | IBM | - | 0.3B | 33k | - | - | - | - | ||
| Granite 4.0 H Small | IBM | - | 32B 9B active at inference time | 128k | - | - | - | - | ||
| Granite 4.1 8B | IBM | - | 8B | 131k | - | - | - | - | ||
| Granite 4.1 3B | IBM | - | 3B | 131k | - | - | - | - | ||
| Granite 4.0 1B | IBM | - | 1.6B | 128k | - | - | - | - | ||
| Granite 4.0 H 350M | IBM | - | 0.3B | 33k | - | - | - | - | ||
| Granite 4.1 30B | IBM | - | 30B | 131k | - | - | - | - | ||
| Granite 4.0 H 1B | IBM | - | 1.5B | 128k | - | - | - | - |