# Claude Sonnet 4.5 vs Gemini 3.1 Flash Lite

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 11× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-gemini-3-1-flash-lite
- Last updated: 2026-10-12
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and Gemini 3.1 Flash Lite in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4.5 leads 47.3 to 37.8.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 8.2% for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 44.1 | 40.8 |
| Rank | 81 | 144 |
| Context | 200K | 1.05M |
| Input $/M | $3 | $0.25 |
| Output $/M | $15 | $1.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.3 (#61)
- Gemini 3.1 Flash Lite: 37.8 (#188)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena WebDev | 1393 | 1256 |
| SciCode | 44.7% | 41.9% |
| WeirdML | 47.7% | 52.2% |
| LMArena Coding | 1489 | 1400 |
| ALE-Bench | 796.15 | 797.73 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.3 (#32)
- Gemini 3.1 Flash Lite: 30.2 (#79)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| DeepResearch Bench | 52.6% | 37.3% |
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#125)
- Gemini 3.1 Flash Lite: 22.9 (#186)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 67.2% |
| NYT Connections (extended) | 37.3% | 8.2% |
| CritPt | 1.1% | 1.1% |
| Chess Puzzles | 12% | 25% |
| EnigmaEval | 6% | 3% |
| LMArena Hard Prompts | 1462 | 1407 |
| DTBench | 83.2% | 76.8% |
| LMCA | 38.8% | 35% |
| Epoch Capabilities Index | 146.84 | 144.47 |
| ForecastBench | 61.9 | 54.4 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| ARC-AGI-1 | 63.7% | — |
| Thematic Generalization | — | 63.3% |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |

## Math

- Claude Sonnet 4.5: 32.3 (#216)
- Gemini 3.1 Flash Lite: 40.7 (#90)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 27.7% |
| OTIS Mock AIME 2024-2025 | 77.8% | 80% |
| LMArena Math | 1449 | 1428 |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#76)
- Gemini 3.1 Flash Lite: 41.9 (#104)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| GPQA Diamond | 82.3% | 81.8% |
| Humanity's Last Exam | 13.7% | 8.6% |
| Vectara Hallucination Rate | 12% | 8.2% |
| LMArena Expert | 1482 | 1398 |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| GPQA (HELM) | 68.6% | — |

## Multimodal

- Claude Sonnet 4.5: 34.8 (#89)
- Gemini 3.1 Flash Lite: 39.4 (#60)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | — | 1240 |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |

## Multilingual

- Claude Sonnet 4.5: 53.4 (#69)
- Gemini 3.1 Flash Lite: 52.3 (#86)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | 1425 | 1411 |
| LMArena Chinese | 1459 | 1461 |
| LMArena French | 1458 | 1424 |
| LMArena German | 1427 | 1429 |
| LMArena Japanese | 1390 | 1413 |
| LMArena Korean | 1403 | 1392 |
| LMArena Russian | 1437 | 1420 |
| LMArena Spanish | 1457 | 1421 |

## Instruction Following

- Claude Sonnet 4.5: 75.0 (#78)
- Gemini 3.1 Flash Lite: 72.7 (#131)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1459 | 1377 |
| IFEval | 85% | — |

## Long Context

- Claude Sonnet 4.5: 45.2 (#46)
- Gemini 3.1 Flash Lite: 42.5 (#122)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1476 | 1394 |

## Writing & Preference

- Claude Sonnet 4.5: 66.5 (#34)
- Gemini 3.1 Flash Lite: 60.9 (#94)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | 1439 | 1416 |
| LMArena Creative Writing | 1442 | 1401 |
| LMArena Multi-Turn | 1465 | 1417 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |

## FAQ

### Is Claude Sonnet 4.5 better than Gemini 3.1 Flash Lite?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 11× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.5 or Gemini 3.1 Flash Lite?

Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or Gemini 3.1 Flash Lite better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 37.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 200K.

### How many benchmarks do Claude Sonnet 4.5 and Gemini 3.1 Flash Lite share?

36 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 3.1 Flash Lite has 38.