Model comparison
Gemma 7B vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 30.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
GoogleSummary
- They share 14 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Inkling in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 27.1.
Side by side
| Gemma 7B | Inkling | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 30.0 | 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 | 27 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Gemma 7B: 30.5 (#294), Inkling: 34.5 (#234)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Coding | 1048 | 1464 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 7B: —, Inkling: 29.6 (#85)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
Gemma 7B: 19.9 (#249), Inkling: 40.4 (#56)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1451 |
| Epoch Capabilities Index | 111.99 | 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% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Too close to call
Gemma 7B: 31.2 (#228), Inkling: 31.3 (#225)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Math | 1066 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| GSM8K | 46.4% | — |
Knowledge Inkling leads
Gemma 7B: 27.3 (#252), Inkling: 55.1 (#49)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Expert | 1001 | 1465 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Inkling leads
Gemma 7B: 25.1 (#287), Inkling: 54.0 (#52)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Non-English | 999 | 1434 |
| LMArena Chinese | 1035 | 1490 |
| LMArena French | 1025 | 1458 |
| LMArena Russian | 993 | 1429 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Spanish | — | 1448 |
Instruction Following Inkling leads
Gemma 7B: 51.5 (#295), Inkling: 75.1 (#71)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Instruction Following | 1017 | 1426 |
Long Context Inkling leads
Gemma 7B: 31.1 (#282), Inkling: 43.8 (#86)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Longer Query | 1022 | 1434 |
Writing & Preference Inkling leads
Gemma 7B: 27.1 (#302), Inkling: 65.2 (#51)
| Benchmark | Gemma 7B | Inkling |
|---|---|---|
| LMArena Text | 1056 | 1441 |
| LMArena Creative Writing | 1024 | 1387 |
| LMArena Multi-Turn | 963 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Gemma 7B better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 30.0 on the Noometry Index.
Is Gemma 7B or Inkling better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Inkling share?
14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Inkling has 41.