Model comparison
Granite 3.1 8b Instruct vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 31.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling-Small leads 59.8 to 35.7.
Side by side
| Granite 3.1 8b Instruct | Inkling-Small | |
|---|---|---|
| Provider | IBM | Thinking Machines Lab |
| Noometry Index | 31.8 | 46.5 |
| Released | — | 2026-07-15 |
| Weights | Open | Open |
| Context window | — | 524K |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 13 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Granite 3.1 8b Instruct: 33.9 (#232), Inkling-Small: 43.3 (#80)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Coding | 1186 | 1451 |
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 23.9 (#113), Inkling-Small: —
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Inkling-Small leads
Granite 3.1 8b Instruct: 21.2 (#204), Inkling-Small: 39.0 (#53)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1424 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |
Math Inkling-Small leads
Granite 3.1 8b Instruct: 30.4 (#210), Inkling-Small: 44.9 (#65)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Math | 1152 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
Knowledge Inkling-Small leads
Granite 3.1 8b Instruct: 30.6 (#218), Inkling-Small: 48.3 (#71)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Expert | 1142 | 1442 |
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |
Multimodal Not comparable
Granite 3.1 8b Instruct: —, Inkling-Small: 38.4 (#59)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
Granite 3.1 8b Instruct: 31.1 (#255), Inkling-Small: 51.7 (#102)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1099 | 1400 |
| LMArena Chinese | 1145 | 1458 |
| LMArena Russian | 1092 | 1392 |
| LMArena French | — | 1438 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1355 |
| LMArena Spanish | — | 1426 |
Instruction Following Inkling-Small leads
Granite 3.1 8b Instruct: 58.9 (#254), Inkling-Small: 73.9 (#112)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1131 | 1397 |
Long Context Inkling-Small leads
Granite 3.1 8b Instruct: 35.2 (#236), Inkling-Small: 42.7 (#113)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1162 | 1401 |
Writing & Preference Inkling-Small leads
Granite 3.1 8b Instruct: 35.7 (#261), Inkling-Small: 59.8 (#102)
| Benchmark | Granite 3.1 8b Instruct | Inkling-Small |
|---|---|---|
| LMArena Text | 1150 | 1413 |
| LMArena Creative Writing | 1129 | 1330 |
| LMArena Multi-Turn | 1108 | 1420 |
| EQ-Bench Creative Writing | — | 1491 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 31.8 on the Noometry Index.
Is Granite 3.1 8b Instruct or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 33.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Inkling-Small share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Inkling-Small has 33.