Model comparison
Gemma 3n E4b IT vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 37.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 2 categories and Inkling in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 34.2.
Side by side
| Gemma 3n E4b IT | Inkling | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 37.3 | 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 | 18 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3n E4b IT: 37.0 (#198), Inkling: 34.5 (#234)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Coding | 1268 | 1464 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Inkling: 29.6 (#85)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
Gemma 3n E4b IT: 19.9 (#247), Inkling: 40.4 (#56)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1451 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 31.5% | — |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), Inkling: 31.3 (#225)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Math | 1251 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
Knowledge Inkling leads
Gemma 3n E4b IT: 34.2 (#198), Inkling: 55.1 (#49)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Expert | 1246 | 1465 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
Multilingual Inkling leads
Gemma 3n E4b IT: 43.4 (#183), Inkling: 54.0 (#52)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Non-English | 1285 | 1434 |
| LMArena Chinese | 1309 | 1490 |
| LMArena French | 1330 | 1458 |
| LMArena German | 1311 | 1446 |
| LMArena Japanese | 1272 | 1429 |
| LMArena Korean | 1259 | 1404 |
| LMArena Russian | 1288 | 1429 |
| LMArena Spanish | 1305 | 1448 |
Instruction Following Inkling leads
Gemma 3n E4b IT: 66.1 (#210), Inkling: 75.1 (#71)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Instruction Following | 1255 | 1426 |
Long Context Inkling leads
Gemma 3n E4b IT: 38.7 (#191), Inkling: 43.8 (#86)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Longer Query | 1276 | 1434 |
Writing & Preference Inkling leads
Gemma 3n E4b IT: 50.1 (#186), Inkling: 65.2 (#51)
| Benchmark | Gemma 3n E4b IT | Inkling |
|---|---|---|
| LMArena Text | 1306 | 1441 |
| LMArena Creative Writing | 1287 | 1387 |
| LMArena Multi-Turn | 1276 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Gemma 3n E4b IT better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 37.3 on the Noometry Index.
Is Gemma 3n E4b IT or Inkling better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 34.5 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Inkling share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Inkling has 41.