granite-4.0-1b: benchmark scores, price and ranking
granite-4.0-1b from IBM ranks #698 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.7), based on 3 benchmark results captured up to 2026-10-13.
- Organisation
- IBM
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-10-28 (source: epoch)
- Aggregate rank
- #698 of 743 (score 42.7)
Relative to other models, granite-4.0-1b is strongest on Chess Puzzles (#109 of 122) and weakest on GPQA Diamond (#267 of 275).
Across the 3 benchmarks where at least ten models are scored, granite-4.0-1b is in the top 10% on 0 and in the top half on 0.
granite-4.0-1b benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Chess Puzzles | 0.0% | #109 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 0.8% | #183 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 24.0% | #267 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
About granite-4.0-1b
granite-4.0-1b is a frontier model from IBM. It was released on 2025-10-28, according to Epoch AI. No API price is listed for it yet. We hold 3 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where granite-4.0-1b stands
On our aggregate score, granite-4.0-1b is #698 of 743 ranked models, in the lower half. Its score is 42.7; the scale is centred on 50, so it sits 7.3 points below the typical model. That beats 6% of the ranked field. Among the 4 ranked IBM models it is #3. The next one up is granite-4.0-micro at 43.2. The next one down is granite-4.0-350m at 41.6.
granite-4.0-1b, benchmark by benchmark
Chess Puzzles is a weak spot. granite-4.0-1b scores 0.0%, #109 of 122, behind 89% of the models measured. The leader, GPT-6 Astra (max), reaches 72.0%. It covers chess tactics puzzles. The board median is 12.5%, so granite-4.0-1b is 12.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME is a weak spot. granite-4.0-1b scores 0.8%, #183 of 189, behind 96% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so granite-4.0-1b is 56.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GPQA Diamond is a weak spot. granite-4.0-1b scores 24.0%, #267 of 275, behind 97% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so granite-4.0-1b is 47.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 3% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#183 of 189) and its weakest is GPQA Diamond (#267 of 275).
Release history
The IBM model released before it was granite-4.0-micro on 2025-10-02, which scores 43.2. The next one was granite-4.0-350m on 2025-10-28, at 41.6.
Reading these numbers
The 3 scores on this page come from 1 source: Epoch AI Benchmarking Hub (3). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #695 gemini-1.5-flash-002 (42.8)
- #696 deepseek-llm-67b-chat (42.8)
- #697 Mistral Large 3 (42.7)
- #699 Qwen2.5-Coder-0.5B-Instruct (42.6)
- #700 Llama-3.1-70B-Instruct (42.6)
- #701 Gemini 1.5 Flash (May 2024) (42.6)
More from IBM
- ollama/granite3-dense:8b (#671, 43.6)
- granite-4.0-micro (#685, 43.2)
- granite-4.0-350m (#722, 41.6)
Compare it on the live leaderboard → · How the aggregate score works