Model comparison
Gemini 3.1 Flash Lite vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 4.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 3 categories and Inkling in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 22.9.
- The biggest single-benchmark swing is WeirdML: 52.2% for Gemini 3.1 Flash Lite and 32.3% for Inkling.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Inkling | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 40.8 | 44.1 |
| Released | 2026-03-03 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 66K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.25 | $1.87 |
| Output $ / M tokens | $1.50 | $4.68 |
| Results tracked | 38 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 37.8 (#188), Inkling: 34.5 (#234)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| LMArena WebDev | 1256 | 1413 |
| SciCode | 41.9% | 47% |
| WeirdML | 52.2% | 32.3% |
| LMArena Coding | 1400 | 1464 |
| ALE-Bench | 797.73 | 946 |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |
Agentic & Tool Use Too close to call
Gemini 3.1 Flash Lite: 30.2 (#79), Inkling: 29.6 (#85)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
| DeepResearch Bench | 37.3% | — |
Reasoning Inkling leads
Gemini 3.1 Flash Lite: 22.9 (#186), Inkling: 40.4 (#56)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| CritPt | 1.1% | 5.4% |
| Chess Puzzles | 25% | 21% |
| LMArena Hard Prompts | 1407 | 1451 |
| DTBench | 76.8% | 87.5% |
| LMCA | 35% | 37.6% |
| Epoch Capabilities Index | 144.47 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 67.2% | — |
| NYT Connections (extended) | 8.2% | — |
| ARC-AGI-1 | — | 79.5% |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| ForecastBench | 54.4 | — |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 40.7 (#90), Inkling: 31.3 (#225)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 33.3% |
| OTIS Mock AIME 2024-2025 | 80% | 88.9% |
| LMArena Math | 1428 | 1479 |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |
Knowledge Inkling leads
Gemini 3.1 Flash Lite: 41.9 (#104), Inkling: 55.1 (#49)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| GPQA Diamond | 81.8% | 88.3% |
| LMArena Expert | 1398 | 1465 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 40.3% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), Inkling: —
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Inkling leads
Gemini 3.1 Flash Lite: 52.3 (#86), Inkling: 54.0 (#52)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| LMArena Non-English | 1411 | 1434 |
| LMArena Chinese | 1461 | 1490 |
| LMArena French | 1424 | 1458 |
| LMArena German | 1429 | 1446 |
| LMArena Japanese | 1413 | 1429 |
| LMArena Korean | 1392 | 1404 |
| LMArena Russian | 1420 | 1429 |
| LMArena Spanish | 1421 | 1448 |
Instruction Following Inkling leads
Gemini 3.1 Flash Lite: 72.7 (#131), Inkling: 75.1 (#71)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| LMArena Instruction Following | 1377 | 1426 |
Long Context Inkling leads
Gemini 3.1 Flash Lite: 42.5 (#122), Inkling: 43.8 (#86)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| LMArena Longer Query | 1394 | 1434 |
Writing & Preference Inkling leads
Gemini 3.1 Flash Lite: 60.9 (#94), Inkling: 65.2 (#51)
| Benchmark | Gemini 3.1 Flash Lite | Inkling |
|---|---|---|
| LMArena Text | 1416 | 1441 |
| LMArena Creative Writing | 1401 | 1387 |
| LMArena Multi-Turn | 1417 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 4.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or Inkling?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Gemini 3.1 Flash Lite or Inkling better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 66K.
How many benchmarks do Gemini 3.1 Flash Lite and Inkling share?
29 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Inkling has 41.