Granite 4.0 H 1B
Granite 4.0 H 1B is behind the leaders in agentic tasks. Too few results yet to rate reasoning, coding, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Safety, Long Context, Math, Multimodal, Multilingual, Instruction Following or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
23results on21benchmarks
- 15 aggregator
- 8 cross-referenced
From 2 sources · latest Oct 8, 2026 · How verification works
Granite 4.0 H 1B benchmark results
23 results on 21 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
47.1% behind the leader1 of 7 ranked benchmarks measured
- 0.00Jun 15, 2026
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond26.26Oct 8, 2026gpqa
- Humanity's Last Exam5.00Oct 8, 2026aa_hle
Show 1 more reasoning resultHide 1 reasoning result
- 24.34Aug 9, 2026
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard0.00Oct 8, 2026aa_terminalbench_hard
- SciCode8.22Sep 4, 2026aa_scicode
0 of 3 ranked benchmarks measured
- 7.00Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench26.19Oct 8, 2026aa_ifbench
- 24.93Aug 9, 2026
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy5.20Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination18.28Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- τ²-Bench Telecom (AA run)19.59Oct 8, 2026aa_tau2
- AA Intelligence5.19Oct 8, 2026aa_intelligence_index
- -72.27Oct 8, 2026
- 6.53Jun 18, 2026
- 2.74Jun 18, 2026
- 50.69Aug 9, 2026
Show 5 more resultsHide 5 results
- AIME25 no tools1.00Aug 9, 2026AIME25
- 69.60Aug 9, 2026
- 80.08Aug 9, 2026
- MATH-500 (EM)47.20Aug 9, 2026MATH-500
- 27.64Aug 9, 2026
Granite 4.0 H 1B: common questions
Who makes Granite 4.0 H 1B?
Granite 4.0 H 1B is made by IBM.
When was Granite 4.0 H 1B released?
Granite 4.0 H 1B was released on Oct 28, 2025, according to Artificial Analysis.
What is Granite 4.0 H 1B good at?
Granite 4.0 H 1B is behind the leaders in agentic tasks. Too few results yet to rate reasoning, coding, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
How many benchmarks has Granite 4.0 H 1B been tested on?
We track 23 results for Granite 4.0 H 1B on 21 benchmarks from 2 sources. The latest was recorded on Oct 8, 2026.
About this record
Where Granite 4.0 H 1B's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- Aug 9, 2026
Where the results come from
Verification: 23 scores · 0 independently verified · 15 aggregator-attributed · 8 vendor cross-reference. How these tiers are assigned
From 2 sources on 2 sites. Artificial Analysis supplies 15 of them. Bars are coloured by trust tier.
- artificialanalysis.ai15
- huggingface.co8