Granite 3.3 8B (Non-reasoning)
Analysis Summary
Granite 3.3 8B (Non-reasoning) sits in the Efficient tier on our leaderboard, ranked #277 of 557 published models on overall intelligence. At $0.030 input and $0.250 output per 1M tokens, it is among the most expensive on the market.
Editorial notes
Granite 3.3 8B Non-reasoning from IBM is an ultra-cheap compact model with very low reasoning and coding scores; its $0.03 input pricing suits only high-volume, low-complexity tasks.
Assessed May 14, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Granite 3.3 8B (Non-reasoning) stack up?
Compare side-by-side with other efficient models.
Model Information
| Provider | IBM |
| Release Date | April 16, 2025 |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.03 | $0.000030 |
| Output | $0.25 | $0.000250 |
