Model comparison
Gemma 2B vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Inkling in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 24.0.
Side by side
| Gemma 2B | Inkling | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 29.6 | 44.1 |
| Released | 2024-02-21 | 2026-07-15 |
| Weights | Open | Open |
| Context window | — | 66K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.87 |
| Output $ / M tokens | — | $4.68 |
| Results tracked | 23 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Gemma 2B: 29.4 (#305), Inkling: 34.5 (#234)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Coding | 1010 | 1464 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Inkling: 29.6 (#85)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
Gemma 2B: 18.8 (#275), Inkling: 40.4 (#56)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Hard Prompts | 989 | 1451 |
| Epoch Capabilities Index | 94.2 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Inkling leads
Gemma 2B: 30.0 (#239), Inkling: 31.3 (#225)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Math | 1009 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Inkling: 55.1 (#49)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1465 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Inkling leads
Gemma 2B: 23.0 (#294), Inkling: 54.0 (#52)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Non-English | 958 | 1434 |
| LMArena Chinese | 986 | 1490 |
| LMArena Russian | 937 | 1429 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Spanish | — | 1448 |
Instruction Following Inkling leads
Gemma 2B: 48.5 (#302), Inkling: 75.1 (#71)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Instruction Following | 970 | 1426 |
Long Context Inkling leads
Gemma 2B: 29.9 (#291), Inkling: 43.8 (#86)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Longer Query | 981 | 1434 |
Writing & Preference Inkling leads
Gemma 2B: 24.0 (#308), Inkling: 65.2 (#51)
| Benchmark | Gemma 2B | Inkling |
|---|---|---|
| LMArena Text | 1002 | 1441 |
| LMArena Creative Writing | 987 | 1387 |
| LMArena Multi-Turn | 945 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Gemma 2B better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 29.6 on the Noometry Index.
Is Gemma 2B or Inkling better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Inkling share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Inkling has 41.