Model comparison
Gemini 3 Flash Preview vs Inkling
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.1 on the Noometry Index.
Last verified . 34 shared benchmarks.
GoogleSummary
- They share 34 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 9 categories and Inkling in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3 Flash Preview leads 51.7 to 31.3.
- The biggest single-benchmark swing is WeirdML: 61.6% for Gemini 3 Flash Preview and 32.3% for Inkling.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Flash Preview | Inkling | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 52.3 | 44.1 |
| Released | 2025-12-17 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 66K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.50 | $1.87 |
| Output $ / M tokens | $3 | $4.68 |
| Results tracked | 59 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Inkling: 34.5 (#234)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| LMArena WebDev | 1439 | 1413 |
| WeirdML | 61.6% | 32.3% |
| LMArena Coding | 1460 | 1464 |
| ALE-Bench | 1,367 | 946 |
| SWE-bench Verified | 75.4% | — |
| FrontierCode | — | 14% |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| GSO | 9.8% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), Inkling: 29.6 (#85)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| τ²-bench Banking | 27.3% | 25% |
| Terminal-Bench | 64.3% | — |
| APEX-Agents | — | 33.8% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Inkling: 40.4 (#56)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| ARC-AGI-2 | 33.6% | 36.5% |
| SimpleBench | 61.1% | 50% |
| ARC-AGI-1 | 84.7% | 79.5% |
| Chess Puzzles | 40% | 21% |
| LMArena Hard Prompts | 1465 | 1451 |
| DTBench | 89.1% | 87.5% |
| LMCA | 43.1% | 37.6% |
| Epoch Capabilities Index | 151.8 | 148.54 |
| NYT Connections (extended) | 83.1% | — |
| CritPt | — | 5.4% |
| Mystery Game Puzzles | 26% | — |
| ForecastBench | 58.5 | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), Inkling: 31.3 (#225)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 33.3% |
| FrontierMath Tier 4 | 17.1% | 4.9% |
| OTIS Mock AIME 2024-2025 | 95.6% | 88.9% |
| ProofBench | 15% | 0% |
| LMArena Math | 1473 | 1479 |
| MathArena Final-Answer Competitions | 67.6% | — |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Inkling: 55.1 (#49)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| GPQA Diamond | 89.4% | 88.3% |
| SimpleQA Verified | 66.8% | 40.3% |
| LMArena Expert | 1462 | 1465 |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), Inkling: —
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Inkling: 54.0 (#52)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| LMArena Non-English | 1458 | 1434 |
| LMArena Chinese | 1511 | 1490 |
| LMArena French | 1477 | 1458 |
| LMArena German | 1497 | 1446 |
| LMArena Japanese | 1489 | 1429 |
| LMArena Korean | 1443 | 1404 |
| LMArena Russian | 1480 | 1429 |
| LMArena Spanish | 1469 | 1448 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), Inkling: 75.1 (#71)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| LMArena Instruction Following | 1437 | 1426 |
Long Context Too close to call
Gemini 3 Flash Preview: 44.4 (#67), Inkling: 43.8 (#86)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| LMArena Longer Query | 1452 | 1434 |
Writing & Preference Too close to call
Gemini 3 Flash Preview: 65.5 (#45), Inkling: 65.2 (#51)
| Benchmark | Gemini 3 Flash Preview | Inkling |
|---|---|---|
| LMArena Text | 1466 | 1441 |
| LMArena Creative Writing | 1457 | 1387 |
| LMArena Multi-Turn | 1471 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Inkling?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.1 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Inkling?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Gemini 3 Flash Preview or Inkling better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 66K.
How many benchmarks do Gemini 3 Flash Preview and Inkling share?
34 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Inkling has 41.