Model comparison
Gemma 2 9B vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.2 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 90% for Inkling-Small.
Side by side
| Gemma 2 9B | Inkling-Small | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 25.9 | 46.5 |
| Released | 2024-06-24 | 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 | 35 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Gemma 2 9B: 29.4 (#304), Inkling-Small: 43.6 (#85)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Coding | 1173 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Inkling-Small leads
Gemma 2 9B: 15.9 (#309), Inkling-Small: 38.6 (#63)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1423 |
| Epoch Capabilities Index | 119.83 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| LiveBench Reasoning | 15.2% | — |
| Mystery Game Puzzles | — | 6% |
| LiveBench Data Analysis | 36.4% | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Inkling-Small leads
Gemma 2 9B: 9.9 (#318), Inkling-Small: 45.1 (#77)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 90% |
| LMArena Math | 1183 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Inkling-Small leads
Gemma 2 9B: 9.7 (#305), Inkling-Small: 48.2 (#77)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| GPQA Diamond | 27.5% | 88.5% |
| LMArena Expert | 1147 | 1442 |
| SimpleQA Verified | — | 19.1% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Inkling-Small: 39.1 (#62)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
Gemma 2 9B: 36.6 (#238), Inkling-Small: 51.7 (#104)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1188 | 1402 |
| LMArena Chinese | 1185 | 1465 |
| LMArena French | 1190 | 1436 |
| LMArena German | 1186 | 1405 |
| LMArena Japanese | 1144 | 1405 |
| LMArena Korean | 1137 | 1363 |
| LMArena Russian | 1200 | 1391 |
| LMArena Spanish | 1200 | 1428 |
Instruction Following Inkling-Small leads
Gemma 2 9B: 57.6 (#269), Inkling-Small: 73.8 (#114)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1178 | 1399 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Inkling-Small leads
Gemma 2 9B: 36.3 (#233), Inkling-Small: 42.7 (#118)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1197 | 1401 |
Writing & Preference Inkling-Small leads
Gemma 2 9B: 32.1 (#281), Inkling-Small: 59.6 (#107)
| Benchmark | Gemma 2 9B | Inkling-Small |
|---|---|---|
| LMArena Text | 1207 | 1414 |
| LMArena Creative Writing | 1206 | 1331 |
| EQ-Bench Creative Writing | 841 | 1491 |
| LMArena Multi-Turn | 1193 | 1418 |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Inkling-Small share?
21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Inkling-Small has 33.