Model comparison
Gemini 2.5 Flash-Lite vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 8.6× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 2.5 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 22.2.
- The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 84.8% for Gemini 3.8 Flash.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
Side by side
| Gemini 2.5 Flash-Lite | Gemini 3.8 Flash | |
|---|---|---|
| Provider | ||
| Noometry Index | 37.0 | 61.8 |
| Released | 2025-06-17 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.10 | $0.75 |
| Output $ / M tokens | $0.40 | $3.75 |
| Results tracked | 33 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 38.5 (#173), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| WeirdML | 35.2% | 84.8% |
| LMArena Coding | 1373 | 1510 |
| ALE-Bench | 325.9 | 1,270 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1584 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 28.0 (#96), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Berkeley Function Calling Leaderboard | 36.9% | — |
| Remote Labor Index | — | 5.8% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |
Reasoning Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 22.2 (#205), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1508 |
| DTBench | 62.8% | 95.7% |
| LMCA | 18.1% | 52.9% |
| Epoch Capabilities Index | 133.94 | 156.71 |
| ARC-AGI-2 | — | 89.2% |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| Surface Evolver Bench | — | 76.9% |
Math Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 38.0 (#144), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Math | 1373 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |
| Omni-MATH | 48% | — |
Knowledge Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 32.5 (#210), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Expert | 1373 | 1524 |
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 29.1 (#114), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1198 | 1314 |
| VPCT | 30% | — |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 49.3 (#134), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1369 | 1491 |
| LMArena Chinese | 1404 | 1554 |
| LMArena French | 1388 | 1498 |
| LMArena German | 1389 | 1493 |
| LMArena Japanese | 1359 | 1502 |
| LMArena Korean | 1360 | 1459 |
| LMArena Russian | 1373 | 1515 |
| LMArena Spanish | 1396 | 1485 |
Instruction Following Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 70.0 (#168), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1367 | 1490 |
| IFEval | 81% | — |
Long Context Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 33.3 (#262), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1373 | 1508 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Gemini 3.8 Flash leads
Gemini 2.5 Flash-Lite: 56.8 (#135), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1379 | 1499 |
| LMArena Creative Writing | 1367 | 1492 |
| LMArena Multi-Turn | 1366 | 1501 |
| EQ-Bench Creative Writing | — | 1748 |
| WildBench | 81.8% | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 8.6× 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 2.5 Flash-Lite or Gemini 3.8 Flash?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.
Is Gemini 2.5 Flash-Lite or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 38.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 2.5 Flash-Lite and Gemini 3.8 Flash share?
23 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Gemini 3.8 Flash has 50.