IBM is a company whose AI models we track in AI Benchmark. In AI Benchmark we track 2 models on IBM with prices, context, speed and usage rates. The highest Intelligence Index belongs to Granite 4.2 8B (5,1). The data is updated every day.
Prices are in dollars per 1M tokens: from $0,06 for input at Granite 4.2 8B up to the more powerful models. Fastest is Granite 4.2 8B with about 112 tokens per second. Below are all the reasoning levels (effort) of each model as separate rows: Intelligence Index score, cost per task, input and output price, cache, time to first token and speed. The Intelligence Index is an overall score from independent Artificial Analysis tests. A higher reasoning level usually gives a better result, but uses more tokens and costs more.
Tracked models2with a separate page
Highest Intelligence Index5,1Granite 4.2 8B
Lowest input price$0,06per 1M tokens, Granite 4.2 8B
Fastest model112tokens/sec., Granite 4.2 8B
Which model from IBM to choose
The choice depends directly on the numbers above. For your task, test with real examples.
All tracked models from IBM
Intelligence Index5,1
Input / 1M$0,06
Output / 1M$0,25
Contextn/a
Speed112 t/s
10,000 requests*$1,85
Granite 4.2 8B is a model by IBM, published in the Artificial Analysis data dated August 2026. Its strongest tier has an Intelligence Index of 5.1 and ranks 72nd out of 82 tracked models. The API price is $0.06 per 1M input and $0,25 for 1 million andзходящand tokens.…
Intelligence Index4,7
Input / 1Mn/a
Output / 1Mn/a
Contextn/a
Speedn/a
10,000 requests*n/a
Granite 4.2 3B is an IBM model, published in Artificial Analysis data dated August 2026. Its strongest level has an Intelligence Index of 4.7 and ranks 74th out of 82 tracked models.
* Example API spend for 10,000 requests of 1000 input and 500 output tokens each. The actual bill depends on the length of the texts.
Compare models with each other
Compare IBM models side by side
Frequently asked questions about IBM
Which models does IBM tracks AI Benchmark?
Currently we track 2 models: Granite 4.2 8B, Granite 4.2 3B. Each has its own page with price, context and usage rates. The list and data are updated every day.
Which is the best model for IBM?
Among the tracked models, the highest Artificial Analysis Intelligence Index belongs to Granite 4.2 8B: 5,1 points. The index is an overall score from several independent tests and does not say which model is best for your specific task.
How much it costs IBM via API?
Prices are per 1M tokens. The cheapest model is Granite 4.2 8B: $0,06 for input and $0,25 for output. The highest output price is $0,25. Monthly app subscriptions are not included in these numbers.
Which model from IBM is the fastest?
Granite 4.2 8B responds fastest among those tracked: about 112 tokens per second according to Artificial Analysis data.
Are open-weight models the models from IBM?
None of the tracked models have open weights. They are used through apps and APIs.
Sources: Artificial Analysis, the official pages of IBM. Last check: 22.11.2026. To the full AI Benchmark