Model comparison
Gemma 2 27B vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 29.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 90% for Inkling-Small.
- Both cost about the same: $0.65 input and $0.65 output per million tokens.
- Inkling-Small accepts more context: 524K tokens versus 8K.
Side by side
| Gemma 2 27B | Inkling-Small | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 29.4 | 46.5 |
| Released | 2024-06-24 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 8K | 524K |
| Max output | 2K | 1.05M |
| Input $ / M tokens | $0.65 | $0.45 |
| Output $ / M tokens | $0.65 | $1.20 |
| Results tracked | 34 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Gemma 2 27B: 34.1 (#246), Inkling-Small: 43.6 (#85)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Coding | 1211 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Inkling-Small leads
Gemma 2 27B: 15.3 (#315), Inkling-Small: 38.6 (#63)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1423 |
| Epoch Capabilities Index | 122.08 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |
Math Inkling-Small leads
Gemma 2 27B: 10.7 (#311), Inkling-Small: 45.1 (#77)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 90% |
| LMArena Math | 1212 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Inkling-Small leads
Gemma 2 27B: 19.0 (#280), Inkling-Small: 48.2 (#77)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| GPQA Diamond | 36.5% | 88.5% |
| LMArena Expert | 1172 | 1442 |
| SimpleQA Verified | — | 19.1% |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multimodal Not comparable
Gemma 2 27B: —, Inkling-Small: 39.1 (#62)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
Gemma 2 27B: 38.6 (#226), Inkling-Small: 51.7 (#104)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1217 | 1402 |
| LMArena Chinese | 1221 | 1465 |
| LMArena French | 1247 | 1436 |
| LMArena German | 1209 | 1405 |
| LMArena Japanese | 1175 | 1405 |
| LMArena Korean | 1174 | 1363 |
| LMArena Russian | 1234 | 1391 |
| LMArena Spanish | 1228 | 1428 |
Instruction Following Inkling-Small leads
Gemma 2 27B: 60.5 (#249), Inkling-Small: 73.8 (#114)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1206 | 1399 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Inkling-Small leads
Gemma 2 27B: 37.3 (#218), Inkling-Small: 42.7 (#118)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1231 | 1401 |
Writing & Preference Inkling-Small leads
Gemma 2 27B: 44.2 (#225), Inkling-Small: 59.6 (#107)
| Benchmark | Gemma 2 27B | Inkling-Small |
|---|---|---|
| LMArena Text | 1231 | 1414 |
| LMArena Creative Writing | 1241 | 1331 |
| LMArena Multi-Turn | 1224 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 8K.
How many benchmarks do Gemma 2 27B and Inkling-Small share?
20 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Inkling-Small has 33.