Thoughts on AI, technology, and the future we're building.
New posts every week
A lab-level profile for IBM, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.
Lab rank
#14
By available Arena average
Models tracked
1
1 open-weight models
Portfolio coverage
44%
Average matched benchmark signals
Fastest model
0.39s
Granite 4.1 8b
Lab profile
The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.
Portfolio read
The portfolio combines 0 proprietary models and 1 open-weight models. Its average available Arena rank is 76, with a best category rank of #76. Average profile coverage is 44%, so model-level gaps remain visible in the cards below.
Best Arena model
Granite 4.1 8b
Best category rank #76
Highest coverage
Granite 4.1 8b
44% matched signals
Fastest response
Granite 4.1 8b
0.39s first token
Category leaders
Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.
Value
Quality, price, latency, and speed
Granite 4.1 8b
value index
Coding
Code Arena, SWE-bench, and output speed
Granite 4.1 8b
coding index
Agents
Search, document, code, and latency
Granite 4.1 8b
agent proxy
Reasoning
Text, document, vision, and mode signals
Not listed
Not enough matched rows for this lab in this suite.
Context
Document, search, and text proxy
Not listed
Not enough matched rows for this lab in this suite.
Models from this lab with both quality and commercial price matches.
Top 1 of 1
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #69 | 51value index | $0.063blended / 1M tokens | 0.39stime to first token | 131 tok/soutput speed | 23quality signal | ArenaArtificial Analysis |
Model portfolio
Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.