Model comparison
Claude 3 Sonnet vs Gemini 1.0 Pro
Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 27.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 7 categories and Gemini 1.0 Pro in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Sonnet leads 42.1 to 36.0.
- The biggest single-benchmark swing is DTBench: 53.6% for Claude 3 Sonnet and 45.9% for Gemini 1.0 Pro.
Side by side
| Claude 3 Sonnet | Gemini 1.0 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.0 | 27.3 |
| Released | 2024-02-29 | 2023-12-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Claude 3 Sonnet: 29.6 (#302), Gemini 1.0 Pro: 32.2 (#275)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1223 | 1108 |
| HumanEval+ | 64% | 55.5% |
| MBPP+ | 69.3% | 61.4% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), Gemini 1.0 Pro: 17.1 (#296)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1109 |
| DTBench | 53.6% | 45.9% |
| Epoch Capabilities Index | 120.7 | 117.04 |
| WinoGrande | 75.1% | — |
Math Claude 3 Sonnet leads
Claude 3 Sonnet: 10.7 (#310), Gemini 1.0 Pro: 9.3 (#321)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 1.1% |
| LMArena Math | 1213 | 1132 |
| MATH Level 5 | 18.2% | 11.2% |
Knowledge Claude 3 Sonnet leads
Claude 3 Sonnet: 21.1 (#276), Gemini 1.0 Pro: 15.6 (#291)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | 40.6% | 34% |
| LMArena Expert | 1173 | 1059 |
| MMLU | 75.9% | 70% |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Gemini 1.0 Pro: —
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), Gemini 1.0 Pro: 33.4 (#252)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1205 | 1138 |
| LMArena Chinese | 1189 | 1124 |
| LMArena French | 1229 | 1145 |
| LMArena German | 1204 | 1125 |
| LMArena Japanese | 1131 | 1023 |
| LMArena Russian | 1227 | 1186 |
| LMArena Spanish | 1204 | 1119 |
| LMArena Korean | 1128 | — |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 62.8 (#235), Gemini 1.0 Pro: 57.6 (#267)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1199 | 1114 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#228), Gemini 1.0 Pro: 34.3 (#249)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1211 | 1132 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), Gemini 1.0 Pro: 36.0 (#264)
| Benchmark | Claude 3 Sonnet | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1218 | 1149 |
| LMArena Creative Writing | 1186 | 1131 |
| LMArena Multi-Turn | 1227 | 1139 |
Frequently asked questions
Is Claude 3 Sonnet better than Gemini 1.0 Pro?
Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 27.3 on the Noometry Index.
Is Claude 3 Sonnet or Gemini 1.0 Pro better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Gemini 1.0 Pro share?
24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemini 1.0 Pro has 24.