# Claude Sonnet 4.6 vs Gemini 1.5 Pro (May 2024)

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-gemini-1-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 10 categories and Gemini 1.5 Pro (May 2024) in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 12.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 23.1% for Gemini 1.5 Pro (May 2024).

## Snapshot

| | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 50.1 | 31.9 |
| Rank | 42 | 253 |
| Context | 1M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.6: 46.0 (#62)
- Gemini 1.5 Pro (May 2024): 33.8 (#239)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| WeirdML | 66.1% | 22.2% |
| LMArena Coding | 1504 | 1294 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1521 | — |
| SciCode | 46.8% | — |
| BigCodeBench Instruct | — | 43.8% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | — | 34% |
| ALE-Bench | 1,327 | — |
| HumanEval+ | — | 79.3% |
| MBPP+ | — | 74.6% |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#26)
- Gemini 1.5 Pro (May 2024): 17.8 (#137)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| TheAgentCompany | — | 3.4% |
| Cybench | — | 7.5% |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| BALROG | — | 21% |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#40)
- Gemini 1.5 Pro (May 2024): 12.3 (#332)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| ARC-AGI-2 | 60.4% | 0.8% |
| LMArena Hard Prompts | 1485 | 1296 |
| DTBench | 89.9% | 59% |
| Epoch Capabilities Index | 152.25 | 131.73 |
| ForecastBench | 62 | 58.4 |
| SimpleBench | — | 27.1% |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| LMCA | 46.5% | — |
| BIG-Bench Hard | — | 89.2% |

## Math

- Claude Sonnet 4.6: 51.9 (#41)
- Gemini 1.5 Pro (May 2024): 24.4 (#260)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 23.1% |
| LMArena Math | 1463 | 1315 |
| ProofBench | 45% | — |
| Omni-MATH | — | 36.4% |
| MATH Level 5 | — | 70.4% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Claude Sonnet 4.6: 51.6 (#60)
- Gemini 1.5 Pro (May 2024): 29.3 (#228)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | 87.4% | 57.2% |
| LMArena Expert | 1500 | 1279 |
| Humanity's Last Exam | — | 4.6% |
| SimpleQA Verified | 35.5% | — |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| Vectara Hallucination Rate | 10.6% | — |
| GPQA (HELM) | — | 53.4% |
| MMLU | — | 86.9% |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#61)
- Gemini 1.5 Pro (May 2024): 36.2 (#72)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | 1283 | 1161 |
| Video-MME | — | 75% |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.6 (#39)
- Gemini 1.5 Pro (May 2024): 45.5 (#169)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1440 | 1312 |
| LMArena Chinese | 1491 | 1331 |
| LMArena French | 1465 | 1301 |
| LMArena German | 1428 | 1286 |
| LMArena Japanese | 1419 | 1292 |
| LMArena Korean | 1411 | 1298 |
| LMArena Russian | 1440 | 1320 |
| LMArena Spanish | 1465 | 1310 |

## Instruction Following

- Claude Sonnet 4.6: 77.6 (#23)
- Gemini 1.5 Pro (May 2024): 68.8 (#180)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1476 | 1297 |
| IFEval | — | 83.7% |

## Long Context

- Claude Sonnet 4.6: 45.3 (#40)
- Gemini 1.5 Pro (May 2024): 39.7 (#164)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1479 | 1308 |

## Writing & Preference

- Claude Sonnet 4.6: 70.4 (#22)
- Gemini 1.5 Pro (May 2024): 52.5 (#167)

| Benchmark | Claude Sonnet 4.6 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1458 | 1319 |
| LMArena Creative Writing | 1435 | 1333 |
| LMArena Multi-Turn | 1464 | 1296 |
| EQ-Bench Creative Writing | 1810 | — |
| WildBench | — | 81.3% |
| EQ-Bench 4 | 1207 | — |

## FAQ

### Is Claude Sonnet 4.6 better than Gemini 1.5 Pro (May 2024)?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 31.9 on the Noometry Index.

### Is Claude Sonnet 4.6 or Gemini 1.5 Pro (May 2024) better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 33.8 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 4.6 and Gemini 1.5 Pro (May 2024) share?

25 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.