# Gemini 2.5 Flash-Lite vs Gemini 3.1 Pro Preview

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 26× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-gemini-3-1-pro-preview
- Last updated: 2026-10-12
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 0 categories and Gemini 3.1 Pro Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 22.2.
- The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 72.1% for Gemini 3.1 Pro Preview.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.

## Snapshot

| | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 37.0 | 56.7 |
| Rank | 211 | 23 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.10 | $2 |
| Output $/M | $0.40 | $12 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash-Lite: 38.5 (#173)
- Gemini 3.1 Pro Preview: 42.5 (#99)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| WeirdML | 35.2% | 72.1% |
| LMArena Coding | 1373 | 1484 |
| ALE-Bench | 325.9 | 1,161 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| MirrorCode | — | 8.9% |
| AlgoTune | — | 2.02 |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 28.0 (#96)
- Gemini 3.1 Pro Preview: 37.7 (#34)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| Berkeley Function Calling Leaderboard | 36.9% | — |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |

## Reasoning

- Gemini 2.5 Flash-Lite: 22.2 (#205)
- Gemini 3.1 Pro Preview: 71.7 (#12)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1485 |
| DTBench | 62.8% | 97.1% |
| LMCA | 18.1% | 53.8% |
| Epoch Capabilities Index | 133.94 | 154.77 |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| Mystery Game Puzzles | — | 34% |
| ForecastBench | — | 59 |

## Math

- Gemini 2.5 Flash-Lite: 38.0 (#144)
- Gemini 3.1 Pro Preview: 62.1 (#34)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Math | 1373 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| Omni-MATH | 48% | — |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.5 (#210)
- Gemini 3.1 Pro Preview: 71.8 (#3)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 10.4% |
| LMArena Expert | 1373 | 1485 |
| GPQA Diamond | — | 94.4% |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 29.1 (#114)
- Gemini 3.1 Pro Preview: 37.9 (#69)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 1198 | 1296 |
| VPCT | 30% | — |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.3 (#134)
- Gemini 3.1 Pro Preview: 57.0 (#12)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1369 | 1477 |
| LMArena Chinese | 1404 | 1529 |
| LMArena French | 1388 | 1487 |
| LMArena German | 1389 | 1491 |
| LMArena Japanese | 1359 | 1493 |
| LMArena Korean | 1360 | 1455 |
| LMArena Russian | 1373 | 1498 |
| LMArena Spanish | 1396 | 1479 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.0 (#168)
- Gemini 3.1 Pro Preview: 77.0 (#32)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1367 | 1466 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#262)
- Gemini 3.1 Pro Preview: 47.4 (#18)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1373 | 1483 |
| Fiction.LiveBench | 47.2% | — |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 56.8 (#135)
- Gemini 3.1 Pro Preview: 66.1 (#37)

| Benchmark | Gemini 2.5 Flash-Lite | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1379 | 1481 |
| LMArena Creative Writing | 1367 | 1482 |
| LMArena Multi-Turn | 1366 | 1488 |
| EQ-Bench Creative Writing | — | 1491 |
| WildBench | 81.8% | — |
| EQ-Bench 4 | — | 1142 |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 26× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash-Lite or Gemini 3.1 Pro Preview?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 2.5 Flash-Lite or Gemini 3.1 Pro Preview better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 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 3.1 Pro Preview share?

24 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Gemini 3.1 Pro Preview has 71.