# Claude Sonnet 4.5 vs Gemini 2.0 Flash (Feb 2025)

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-gemini-2-0-flash
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and Gemini 2.0 Flash (Feb 2025) in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4.5 leads 47.8 to 28.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 71.4% for Claude Sonnet 4.5 and 13.5% for Gemini 2.0 Flash (Feb 2025).

## Snapshot

| | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 44.0 | 34.8 |
| Rank | 76 | 223 |
| Context | 1M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.8 (#54)
- Gemini 2.0 Flash (Feb 2025): 28.2 (#308)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 71.4% | 13.5% |
| WeirdML | 47.7% | 25.8% |
| LMArena Coding | 1489 | 1351 |
| SWE-bench Verified | 71.3% | — |
| Aider Polyglot | — | 38.2% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| BigCodeBench Instruct | — | 45.9% |
| LiveBench Coding | — | 63.4% |
| BigCodeBench Complete | — | 59.9% |
| CadEval | — | 30% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.1 (#30)
- Gemini 2.0 Flash (Feb 2025): 28.0 (#85)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| TheAgentCompany | — | 11.4% |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#113)
- Gemini 2.0 Flash (Feb 2025): 15.2 (#308)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| ARC-AGI-2 | 13.6% | 1.3% |
| SimpleBench | 54.3% | 31.1% |
| Kagi LLM Benchmark | 57.9% | 37.8% |
| EnigmaEval | 6% | 1.1% |
| LMArena Hard Prompts | 1462 | 1346 |
| DTBench | 83.2% | 63.2% |
| Epoch Capabilities Index | 146.84 | 135.36 |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 78.2% |
| Mystery Game Puzzles | 17% | — |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 38.8% | — |
| ForecastBench | 61.9 | — |
| LiveBench | — | 66.9% |

## Math

- Claude Sonnet 4.5: 31.9 (#190)
- Gemini 2.0 Flash (Feb 2025): 36.1 (#127)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 57.8% |
| Omni-MATH | 55.3% | 45.9% |
| LMArena Math | 1448 | 1351 |
| MATH Level 5 | 97.7% | 82.2% |
| FrontierMath (Feb 2025 set) | 15.2% | 1.7% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| LiveBench Math | — | 75.8% |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#70)
- Gemini 2.0 Flash (Feb 2025): 32.0 (#207)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| GPQA Diamond | 82.3% | 64.1% |
| Humanity's Last Exam | 13.7% | 6.6% |
| MMLU-Pro | 86.9% | 73.7% |
| GPQA (HELM) | 68.6% | 55.6% |
| LMArena Expert | 1483 | 1340 |
| SimpleQA Verified | 30.7% | — |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 12% | — |
| MMLU | — | 79.7% |

## Multimodal

- Claude Sonnet 4.5: 34.1 (#84)
- Gemini 2.0 Flash (Feb 2025): 35.9 (#74)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | — | 1158 |
| GeoBench | — | 77% |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |

## Multilingual

- Claude Sonnet 4.5: 53.6 (#65)
- Gemini 2.0 Flash (Feb 2025): 47.6 (#144)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1425 | 1342 |
| LMArena Chinese | 1459 | 1373 |
| LMArena French | 1459 | 1390 |
| LMArena German | 1427 | 1354 |
| LMArena Japanese | 1390 | 1293 |
| LMArena Korean | 1403 | 1314 |
| LMArena Russian | 1436 | 1351 |
| LMArena Spanish | 1457 | 1363 |

## Instruction Following

- Claude Sonnet 4.5: 75.2 (#74)
- Gemini 2.0 Flash (Feb 2025): 74.6 (#91)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| IFEval | 85% | 84.1% |
| LMArena Instruction Following | 1459 | 1336 |
| LiveBench Instruction Following | — | 85.8% |

## Long Context

- Claude Sonnet 4.5: 45.2 (#45)
- Gemini 2.0 Flash (Feb 2025): 38.1 (#198)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Longer Query | 1476 | 1345 |
| Fiction.LiveBench | — | 61.1% |

## Writing & Preference

- Claude Sonnet 4.5: 66.7 (#33)
- Gemini 2.0 Flash (Feb 2025): 49.8 (#184)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1439 | 1354 |
| LMArena Creative Writing | 1442 | 1340 |
| EQ-Bench Creative Writing | 1678 | 1128 |
| WildBench | 85.4% | 80% |
| LMArena Multi-Turn | 1465 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| LiveBench Language | — | 51.3% |

## FAQ

### Is Claude Sonnet 4.5 better than Gemini 2.0 Flash (Feb 2025)?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 34.8 on the Noometry Index.

### Is Claude Sonnet 4.5 or Gemini 2.0 Flash (Feb 2025) better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 28.2 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 4.5 and Gemini 2.0 Flash (Feb 2025) share?

36 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.