Model comparison
Gemma 4 26B A4B IT vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 43.1 on the Noometry Index. Gemma 4 26B A4B IT costs 5.3× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 5 categories and Inkling-Small in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 21.1.
- The biggest single-benchmark swing is GPQA Diamond: 73.2% for Gemma 4 26B A4B IT and 88.5% for Inkling-Small.
- Gemma 4 26B A4B IT is cheaper at $0.0765 / $0.26 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Gemma 4 26B A4B IT | Inkling-Small | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 43.1 | 46.5 |
| Released | 2026-04-02 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 262K | 524K |
| Max output | 33K | 1.05M |
| Input $ / M tokens | $0.0765 | $0.45 |
| Output $ / M tokens | $0.26 | $1.20 |
| Results tracked | 28 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Gemma 4 26B A4B IT: 38.8 (#156), Inkling-Small: 43.3 (#80)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1359 | 1408 |
| SciCode | 40% | 48.7% |
| LMArena Coding | 1446 | 1451 |
| WeirdML | 35.2% | — |
| ALE-Bench | 927.17 | — |
Reasoning Inkling-Small leads
Gemma 4 26B A4B IT: 21.1 (#205), Inkling-Small: 39.0 (#53)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| CritPt | 0% | 8.3% |
| Chess Puzzles | 6% | 18% |
| LMArena Hard Prompts | 1438 | 1424 |
| Epoch Capabilities Index | 141.85 | 150.13 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| Mystery Game Puzzles | — | 6% |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
Math Too close to call
Gemma 4 26B A4B IT: 45.7 (#61), Inkling-Small: 44.9 (#65)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 90% |
| LMArena Math | 1469 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
Knowledge Inkling-Small leads
Gemma 4 26B A4B IT: 45.6 (#79), Inkling-Small: 48.3 (#71)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| GPQA Diamond | 73.2% | 88.5% |
| LMArena Expert | 1447 | 1442 |
| SimpleQA Verified | — | 19.1% |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 39.9 (#43), Inkling-Small: 38.4 (#59)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| LMArena Vision | 1260 | 1235 |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.3 (#68), Inkling-Small: 51.7 (#102)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1422 | 1400 |
| LMArena Chinese | 1495 | 1458 |
| LMArena French | 1459 | 1438 |
| LMArena Russian | 1434 | 1392 |
| LMArena Spanish | 1415 | 1426 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1355 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 75.0 (#78), Inkling-Small: 73.9 (#112)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1420 | 1397 |
Long Context Too close to call
Gemma 4 26B A4B IT: 43.6 (#87), Inkling-Small: 42.7 (#113)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1427 | 1401 |
Writing & Preference Too close to call
Gemma 4 26B A4B IT: 58.8 (#110), Inkling-Small: 59.8 (#102)
| Benchmark | Gemma 4 26B A4B IT | Inkling-Small |
|---|---|---|
| LMArena Text | 1434 | 1413 |
| LMArena Creative Writing | 1401 | 1330 |
| EQ-Bench Creative Writing | 1305 | 1491 |
| LMArena Multi-Turn | 1442 | 1420 |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 43.1 on the Noometry Index. Gemma 4 26B A4B IT costs 5.3× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 26B A4B IT or Inkling-Small?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0765 per million input tokens and $0.26 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Gemma 4 26B A4B IT or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 262K.
How many benchmarks do Gemma 4 26B A4B IT and Inkling-Small share?
23 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Inkling-Small has 33.