# Claude 2 vs Gemini 3.5 Flash Lite

> Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 25.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-gemini-3-5-flash-lite
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Claude 2 scores higher in 0 categories and Gemini 3.5 Flash Lite in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.1 to 16.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 2 and 71.1% for Gemini 3.5 Flash Lite.

## Snapshot

| | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 25.0 | 41.5 |
| Rank | 346 | 133 |
| Context | — | 1.05M |
| Input $/M | — | $0.30 |
| Output $/M | — | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2: —
- Gemini 3.5 Flash Lite: 42.4 (#104)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena WebDev | — | 1440 |
| SciCode | — | 41.3% |
| WeirdML | — | 39% |
| LMArena Coding | — | 1453 |
| ALE-Bench | — | 765.27 |
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- Gemini 3.5 Flash Lite: 25.7 (#107)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| APEX-Agents | — | 29.3% |
| GDP.pdf | — | 10% |

## Reasoning

- Claude 2: 21.7 (#216)
- Gemini 3.5 Flash Lite: 27.8 (#114)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| DTBench | 51.9% | 83.5% |
| Epoch Capabilities Index | 120.13 | 145.13 |
| ARC-AGI-2 | — | 10.3% |
| NYT Connections (extended) | — | 60.4% |
| ARC-AGI-1 | — | 53.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 22% |
| LMArena Hard Prompts | — | 1441 |
| Mystery Game Puzzles | — | 19% |
| LMCA | — | 37.6% |

## Math

- Claude 2: 9.3 (#320)
- Gemini 3.5 Flash Lite: 25.9 (#264)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 71.1% |
| FrontierMath (Tiers 1-3) | — | 26% |
| FrontierMath Tier 4 | — | 0% |
| ProofBench | — | 13% |
| LMArena Math | — | 1433 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 16.9 (#287)
- Gemini 3.5 Flash Lite: 50.1 (#72)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| GPQA Diamond | 34.7% | 83.3% |
| LMArena Expert | — | 1435 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- Gemini 3.5 Flash Lite: 41.1 (#40)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Vision | — | 1268 |

## Multilingual

- Claude 2: —
- Gemini 3.5 Flash Lite: 53.5 (#63)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1469 |
| LMArena French | — | 1451 |
| LMArena German | — | 1454 |
| LMArena Japanese | — | 1427 |
| LMArena Korean | — | 1407 |
| LMArena Russian | — | 1443 |
| LMArena Spanish | — | 1442 |

## Instruction Following

- Claude 2: —
- Gemini 3.5 Flash Lite: 74.8 (#85)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Instruction Following | — | 1420 |

## Long Context

- Claude 2: —
- Gemini 3.5 Flash Lite: 43.9 (#84)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Longer Query | — | 1435 |

## Writing & Preference

- Claude 2: —
- Gemini 3.5 Flash Lite: 64.2 (#57)

| Benchmark | Claude 2 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Text | — | 1435 |
| LMArena Creative Writing | — | 1420 |
| EQ-Bench Creative Writing | — | 1559 |
| LMArena Multi-Turn | — | 1445 |

## FAQ

### Is Claude 2 better than Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 25.0 on the Noometry Index.

### How many benchmarks do Claude 2 and Gemini 3.5 Flash Lite share?

4 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Gemini 3.5 Flash Lite has 39.