Model comparison
Granite 4.1 8b vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 37.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. Granite 4.1 8b scores higher in 1 category and Inkling in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 36.1.
Side by side
| Granite 4.1 8b | Inkling | |
|---|---|---|
| Provider | IBM | Thinking Machines Lab |
| Noometry Index | 37.4 | 44.1 |
| Released | — | 2026-07-15 |
| Weights | Open | Open |
| Context window | — | 66K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.87 |
| Output $ / M tokens | — | $4.68 |
| Results tracked | 13 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Granite 4.1 8b: 30.1 (#297), Inkling: 34.5 (#234)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena WebDev | 1192 | 1413 |
| LMArena Coding | 1312 | 1464 |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
Agentic & Tool Use Not comparable
Granite 4.1 8b: —, Inkling: 29.6 (#85)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
Granite 4.1 8b: 25.7 (#143), Inkling: 40.4 (#56)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1451 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |
Math Granite 4.1 8b leads
Granite 4.1 8b: 36.4 (#166), Inkling: 31.3 (#225)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Math | 1312 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
Knowledge Inkling leads
Granite 4.1 8b: 36.1 (#174), Inkling: 55.1 (#49)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Expert | 1309 | 1465 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
Multilingual Inkling leads
Granite 4.1 8b: 41.7 (#204), Inkling: 54.0 (#52)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Non-English | 1261 | 1434 |
| LMArena Chinese | 1337 | 1490 |
| LMArena Russian | 1240 | 1429 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Spanish | — | 1448 |
Instruction Following Inkling leads
Granite 4.1 8b: 66.9 (#203), Inkling: 75.1 (#71)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Instruction Following | 1269 | 1426 |
Long Context Inkling leads
Granite 4.1 8b: 38.7 (#193), Inkling: 43.8 (#86)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Longer Query | 1275 | 1434 |
Writing & Preference Inkling leads
Granite 4.1 8b: 48.1 (#204), Inkling: 65.2 (#51)
| Benchmark | Granite 4.1 8b | Inkling |
|---|---|---|
| LMArena Text | 1290 | 1441 |
| LMArena Creative Writing | 1251 | 1387 |
| LMArena Multi-Turn | 1268 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Granite 4.1 8b better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 37.4 on the Noometry Index.
Is Granite 4.1 8b or Inkling better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 30.1 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Inkling share?
13 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Inkling has 41.