# Claude Sonnet 4.5 vs Gemini 2.5 Flash

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 7.1× 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-2-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 45

## Summary

- They share 45 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and Gemini 2.5 Flash in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.7 to 54.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 71.4% for Claude Sonnet 4.5 and 28.7% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 44.0 | 39.0 |
| Rank | 76 | 162 |
| Context | 1M | 1.05M |
| Input $/M | $3 | $0.30 |
| Output $/M | $15 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.8 (#54)
- Gemini 2.5 Flash: 35.5 (#210)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| SWE-bench Verified (bash only) | 71.4% | 28.7% |
| WeirdML | 47.7% | 41.9% |
| LMArena Coding | 1489 | 1424 |
| ALE-Bench | 796.15 | 661.88 |
| SWE-bench Verified | 71.3% | — |
| Aider Polyglot | — | 55.1% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.1 (#30)
- Gemini 2.5 Flash: 30.6 (#67)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | 46.5% | 17.1% |
| Berkeley Function Calling Leaderboard | 73.2% | 56.2% |
| Vending-Bench 2 | 3,839 | 548.84 |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| TheAgentCompany | — | 41.1% |
| 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% | — |
| BALROG | — | 33.5% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#113)
- Gemini 2.5 Flash: 18.2 (#271)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| ARC-AGI-2 | 13.6% | 2.5% |
| SimpleBench | 54.3% | 41.2% |
| Kagi LLM Benchmark | 57.9% | 56.8% |
| ARC-AGI-1 | 63.7% | 33.3% |
| CritPt | 1.1% | 1.1% |
| EnigmaEval | 6% | 2.7% |
| LMArena Hard Prompts | 1462 | 1422 |
| DTBench | 83.2% | 76.5% |
| LMCA | 38.8% | 27.5% |
| Epoch Capabilities Index | 146.84 | 143.04 |
| ForecastBench | 61.9 | 60.6 |
| NYT Connections (extended) | 37.3% | — |
| Chess Puzzles | 12% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |

## Math

- Claude Sonnet 4.5: 31.9 (#190)
- Gemini 2.5 Flash: 38.1 (#87)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 73.1% |
| Omni-MATH | 55.3% | 38.5% |
| LMArena Math | 1448 | 1415 |
| FrontierMath (Feb 2025 set) | 15.2% | 4.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| MATH Level 5 | 97.7% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#70)
- Gemini 2.5 Flash: 36.1 (#162)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| Humanity's Last Exam | 13.7% | 12.1% |
| MMLU-Pro | 86.9% | 63.9% |
| Vectara Hallucination Rate | 12% | 7.8% |
| GPQA (HELM) | 68.6% | 39% |
| LMArena Expert | 1483 | 1426 |
| GPQA Diamond | 82.3% | — |
| SimpleQA Verified | 30.7% | — |
| Confabulations | — | 16.8% |

## Multimodal

- Claude Sonnet 4.5: 34.1 (#84)
- Gemini 2.5 Flash: 41.2 (#31)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| VPCT | 39.8% | 46.2% |
| LMArena Vision | — | 1254 |
| GeoBench | — | 76% |
| LMArena Document | 1450 | — |
| SpatialViz-Bench | — | 36.9% |

## Multilingual

- Claude Sonnet 4.5: 53.6 (#65)
- Gemini 2.5 Flash: 52.5 (#83)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1425 | 1410 |
| LMArena Chinese | 1459 | 1450 |
| LMArena French | 1459 | 1433 |
| LMArena German | 1427 | 1419 |
| LMArena Japanese | 1390 | 1403 |
| LMArena Korean | 1403 | 1385 |
| LMArena Russian | 1436 | 1415 |
| LMArena Spanish | 1457 | 1421 |

## Instruction Following

- Claude Sonnet 4.5: 75.2 (#74)
- Gemini 2.5 Flash: 75.9 (#50)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| IFEval | 85% | 89.8% |
| LMArena Instruction Following | 1459 | 1405 |

## Long Context

- Claude Sonnet 4.5: 45.2 (#45)
- Gemini 2.5 Flash: 47.5 (#16)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1476 | 1419 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- Claude Sonnet 4.5: 66.7 (#33)
- Gemini 2.5 Flash: 54.0 (#153)

| Benchmark | Claude Sonnet 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1439 | 1417 |
| LMArena Creative Writing | 1442 | 1400 |
| EQ-Bench Creative Writing | 1678 | 1137 |
| WildBench | 85.4% | 81.7% |
| LMArena Multi-Turn | 1465 | 1408 |
| Short-Story Creative Writing | — | 76.5% |

## FAQ

### Is Claude Sonnet 4.5 better than Gemini 2.5 Flash?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 7.1× 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 2.5 Flash?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or Gemini 2.5 Flash better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 35.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Sonnet 4.5 and Gemini 2.5 Flash share?

45 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 2.5 Flash has 54.