IBM model product
0 family, released May 2025.
Updated Aug 17, 2026. Default version: IBM Granite 4.0 Tiny Preview
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for IBM Granite 4.0 Tiny Preview.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAttaQ | Score86.1% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkPopQA | Score22.9% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkAlpacaEval 2.0 | Score35.2% | Rank04 | Participants4 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkHumanEval+ | Score78.3% | Rank06 | Participants10 | Percentile44.4% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score58.1% | Rank10 | Participants18 | Percentile47.1% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score55.7% | Rank16 | Participants21 | Percentile25.0% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score26.7% | Rank26 | Participants26 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkDROP | Score46.2% | Rank28 | Participants30 | Percentile6.9% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score82.4% | Rank42 | Participants66 | Percentile36.9% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score70.1% | Rank44 | Participants48 | Percentile8.5% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score63.0% | Rank64 | Participants67 | Percentile4.5% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score60.4% | Rank97 | Participants101 | Percentile4.0% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for IBM Granite 4.0 Tiny Preview. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionIBM Granite 4.0 Tiny Preview | Released | LLMBoard0.0 | Parameters7B | ContextN/A | Max outputN/A | Open weightsNo | LicenseApache 2.0 |
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about IBM Granite 4.0 Tiny and its available data.
0 family, released May 2025. It utilizes a novel hybrid Mamba-2/Transformer, fine-grained mixture of experts (MoE) architecture (7B total parameters, 1B active at inference).
5T tokens) but demonstrates significant memory efficiency and performance potential, validated for at least 128K context length without positional encoding.
Data as of 2026-08-17.
Common questions about IBM Granite 4.0 Tiny.
IBM Granite 4.0 Tiny's default version was released on May 2, 2025.
No official standard PAYG price is currently available for IBM Granite 4.0 Tiny.
IBM Granite 4.0 Tiny was created by IBM.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.
Nearby ranked alternatives include Llama 3.2 3B, North Micro Vision, Phi 3.5 vision.