Granite 4.1 8Bopen
IBM
17.4#415 of 427 overall
- Input / output
- free / free US$ per 1M tokens
- Context
- — tokens
- Release
- 04/29/2026 release date
- Weights
- Open
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 5 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | Elo Arena |
|---|---|---|---|---|
| Granite 3.0 8B Instruct | — | — | — | 1096 |
| Granite 3.1 8B Instruct | — | — | — | 1150 |
| Granite 3.3 8B | 04/16/2025 | 32.5 | #329 | — |
| Granite 4.1 8B | 04/29/2026 | 17.4 | #415 | 1291 |
| Granite 4.2 8B | 08/31/2026 | 31.8 | #336 | 1319 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1291 | 13% | LMArena |
| Arena WebDev (Elo) weight 1 | 1192 | 3% | LMArena |
| Humanity's Last Exam weight 1 | 3.8 | 8% | Artificial Analysis |
| GPQA Diamond | 43.3 | 23% | Artificial Analysis |
| Long-context reasoning | 13.3 | 20% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Coding | 26.7 | #115 | Arena WebDev (Elo) |
| Reasoning | 27.2 | #382 | Humanity's Last Exam, GPQA Diamond |
| Research | 35.2 | #285 | Long-context reasoning |
| Design | 26.7 | #115 | Arena WebDev (Elo) |
| Chat | 31.3 | #172 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.