# Claude 3 Opus vs Gemini 1.0 Pro

> Claude 3 Opus is the stronger model overall, scoring 29.3 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-opus-vs-gemini-1-0-pro
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3 Opus scores higher in 7 categories and Gemini 1.0 Pro in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Opus leads 47.4 to 36.2.
- The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 11.2% for Gemini 1.0 Pro.

## Snapshot

| | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 29.3 | 27.1 |
| Rank | 300 | 327 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Opus: 32.4 (#261)
- Gemini 1.0 Pro: 31.6 (#270)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1264 | 1108 |
| HumanEval+ | 77.4% | 55.5% |
| MBPP+ | 73.3% | 61.4% |
| WeirdML | 19.2% | — |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |

## Agentic & Tool Use

- Claude 3 Opus: 24.3 (#110)
- Gemini 1.0 Pro: —

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |

## Reasoning

- Claude 3 Opus: 14.2 (#318)
- Gemini 1.0 Pro: 16.4 (#292)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1109 |
| DTBench | 61.6% | 45.9% |
| Epoch Capabilities Index | 126.91 | 116.97 |
| SimpleBench | 23.5% | — |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |

## Math

- Claude 3 Opus: 13.9 (#293)
- Gemini 1.0 Pro: 8.7 (#315)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 1.1% |
| LMArena Math | 1273 | 1132 |
| MATH Level 5 | 37.5% | 11.2% |
| LiveBench Math | 43.6% | — |

## Knowledge

- Claude 3 Opus: 24.5 (#262)
- Gemini 1.0 Pro: 15.5 (#286)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | 47.2% | 34% |
| LMArena Expert | 1223 | 1059 |
| MMLU | 84.6% | 70% |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |

## Multimodal

- Claude 3 Opus: 26.6 (#112)
- Gemini 1.0 Pro: —

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Vision | 1023 | — |

## Multilingual

- Claude 3 Opus: 41.6 (#202)
- Gemini 1.0 Pro: 33.5 (#247)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1258 | 1138 |
| LMArena Chinese | 1248 | 1124 |
| LMArena French | 1274 | 1144 |
| LMArena German | 1258 | 1125 |
| LMArena Japanese | 1204 | 1023 |
| LMArena Russian | 1280 | 1186 |
| LMArena Spanish | 1246 | 1118 |
| LMArena Korean | 1187 | — |

## Instruction Following

- Claude 3 Opus: 64.3 (#223)
- Gemini 1.0 Pro: 57.9 (#262)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1248 | 1114 |
| LiveBench Instruction Following | 63.9% | — |

## Long Context

- Claude 3 Opus: 38.2 (#197)
- Gemini 1.0 Pro: 34.3 (#244)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1259 | 1132 |

## Writing & Preference

- Claude 3 Opus: 47.4 (#208)
- Gemini 1.0 Pro: 36.2 (#259)

| Benchmark | Claude 3 Opus | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1262 | 1149 |
| LMArena Creative Writing | 1235 | 1130 |
| LMArena Multi-Turn | 1275 | 1139 |
| LiveBench Language | 50.4% | — |

## FAQ

### Is Claude 3 Opus better than Gemini 1.0 Pro?

Claude 3 Opus is the stronger model overall, scoring 29.3 to 27.1 on the Noometry Index.

### Is Claude 3 Opus or Gemini 1.0 Pro better for coding?

They score almost the same on coding (32.4 vs 31.6); test both on your own repository before choosing.

### How many benchmarks do Claude 3 Opus and Gemini 1.0 Pro share?

24 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemini 1.0 Pro has 24.