Model comparison
Gemini 3.1 Flash Lite vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.7× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 0 categories and Gemini 3.8 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 22.9.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 97.4% for Gemini 3.8 Flash.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
Side by side
| Gemini 3.1 Flash Lite | Gemini 3.8 Flash | |
|---|---|---|
| Provider | ||
| Noometry Index | 40.8 | 61.8 |
| Released | 2026-03-03 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.25 | $0.75 |
| Output $ / M tokens | $1.50 | $3.75 |
| Results tracked | 38 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 37.8 (#188), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena WebDev | 1256 | 1584 |
| SciCode | 41.9% | 56.6% |
| WeirdML | 52.2% | 84.8% |
| LMArena Coding | 1400 | 1510 |
| ALE-Bench | 797.73 | 1,270 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| FrontierSWE | — | 19.6% |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 30.2 (#79), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Remote Labor Index | — | 5.8% |
| DeepResearch Bench | 37.3% | — |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |
Reasoning Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 22.9 (#186), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| NYT Connections (extended) | 8.2% | 97.4% |
| CritPt | 1.1% | 18.3% |
| Chess Puzzles | 25% | 61% |
| LMArena Hard Prompts | 1407 | 1508 |
| DTBench | 76.8% | 95.7% |
| LMCA | 35% | 52.9% |
| Epoch Capabilities Index | 144.47 | 156.71 |
| ARC-AGI-2 | — | 89.2% |
| Kagi LLM Benchmark | 67.2% | — |
| ARC-AGI-1 | — | 98.5% |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| Mystery Game Puzzles | — | 47% |
| Surface Evolver Bench | — | 76.9% |
| ForecastBench | 54.4 | — |
Math Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 40.7 (#90), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 68.4% |
| OTIS Mock AIME 2024-2025 | 80% | 98.9% |
| LMArena Math | 1428 | 1528 |
| FrontierMath Tier 4 | — | 22% |
| ProofBench | — | 48% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 41.9 (#104), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 81.8% | 95.4% |
| Humanity's Last Exam | 8.6% | 44.5% |
| LMArena Expert | 1398 | 1524 |
| SimpleQA Verified | — | 69.7% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 39.4 (#60), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1240 | 1314 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 52.3 (#86), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1411 | 1491 |
| LMArena Chinese | 1461 | 1554 |
| LMArena French | 1424 | 1498 |
| LMArena German | 1429 | 1493 |
| LMArena Japanese | 1413 | 1502 |
| LMArena Korean | 1392 | 1459 |
| LMArena Russian | 1420 | 1515 |
| LMArena Spanish | 1421 | 1485 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 72.7 (#131), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1377 | 1490 |
Long Context Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 42.5 (#122), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1394 | 1508 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.1 Flash Lite: 60.9 (#94), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Gemini 3.1 Flash Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1416 | 1499 |
| LMArena Creative Writing | 1401 | 1492 |
| LMArena Multi-Turn | 1417 | 1501 |
| EQ-Bench Creative Writing | — | 1748 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.7× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or Gemini 3.8 Flash?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.
Is Gemini 3.1 Flash Lite or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.1 Flash Lite and Gemini 3.8 Flash share?
32 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Gemini 3.8 Flash has 50.