Model comparison
Claude 3.5 Sonnet vs Gemini 1.5 Pro (May 2024)
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 32.1 on the Noometry Index.
Last verified . 43 shared benchmarks.
GoogleSummary
- They share 43 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 6 categories and Gemini 1.5 Pro (May 2024) in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude 3.5 Sonnet leads 32.3 to 17.9.
- The biggest single-benchmark swing is TheAgentCompany: 24% for Claude 3.5 Sonnet and 3.4% for Gemini 1.5 Pro (May 2024).
Side by side
| Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.6 | 32.1 |
| Released | 2024-06-20 | 2024-02-15 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Gemini 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| WeirdML | 40% | 22.2% |
| BigCodeBench Instruct | 46.8% | 43.8% |
| LMArena Coding | 1342 | 1294 |
| BigCodeBench Complete | 58.6% | 57.5% |
| CadEval | 48% | 34% |
| HumanEval+ | 81.7% | 79.3% |
| MBPP+ | 74.3% | 74.6% |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| LiveBench Coding | 67.1% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| TheAgentCompany | 24% | 3.4% |
| Cybench | 17.5% | 7.5% |
| BALROG | 32.6% | 21% |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| SimpleBench | 41.4% | 27.1% |
| LMArena Hard Prompts | 1305 | 1296 |
| DTBench | 67.8% | 59% |
| Epoch Capabilities Index | 133.55 | 131.73 |
| ForecastBench | 60.7 | 58.4 |
| ARC-AGI-2 | — | 0.8% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| BIG-Bench Hard | — | 89.2% |
| LiveBench | 59% | — |
Math Gemini 1.5 Pro (May 2024) leads
Claude 3.5 Sonnet: 19.2 (#288), Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 23.1% |
| Omni-MATH | 27.6% | 36.4% |
| LMArena Math | 1307 | 1315 |
| MATH Level 5 | 56.9% | 70.4% |
| LiveBench Math | 52.3% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
Claude 3.5 Sonnet: 28.6 (#245), Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | 55.3% | 57.2% |
| Humanity's Last Exam | 4.1% | 4.6% |
| MMLU-Pro | 77.7% | 73.7% |
| Confabulations | 19.9% | 13.5% |
| GPQA (HELM) | 56.5% | 53.4% |
| LMArena Expert | 1265 | 1279 |
| MMLU | 87.3% | 86.9% |
Multimodal Gemini 1.5 Pro (May 2024) leads
Claude 3.5 Sonnet: 26.5 (#120), Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | 1125 | 1161 |
| Video-MME | 60% | 75% |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Claude 3.5 Sonnet: 43.2 (#185), Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1283 | 1312 |
| LMArena Chinese | 1272 | 1331 |
| LMArena French | 1305 | 1302 |
| LMArena German | 1297 | 1286 |
| LMArena Japanese | 1234 | 1292 |
| LMArena Korean | 1200 | 1298 |
| LMArena Russian | 1306 | 1320 |
| LMArena Spanish | 1290 | 1311 |
Instruction Following Too close to call
Claude 3.5 Sonnet: 68.8 (#182), Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| IFEval | 85.5% | 83.7% |
| LMArena Instruction Following | 1297 | 1297 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#167), Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1311 | 1308 |
Writing & Preference Too close to call
Claude 3.5 Sonnet: 52.9 (#164), Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | Claude 3.5 Sonnet | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1298 | 1319 |
| LMArena Creative Writing | 1292 | 1333 |
| WildBench | 79.2% | 81.3% |
| LMArena Multi-Turn | 1326 | 1296 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemini 1.5 Pro (May 2024)?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 32.1 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemini 1.5 Pro (May 2024) better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 34.2 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemini 1.5 Pro (May 2024) share?
43 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.