Model comparison
Claude Sonnet 4.5 vs Gemini 1.5 Pro (May 2024)
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 32.1 on the Noometry Index.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 9 categories and Gemini 1.5 Pro (May 2024) in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4.5 leads 38.3 to 17.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 23.1% for Gemini 1.5 Pro (May 2024).
Side by side
| Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 44.1 | 32.1 |
| Released | 2025-09-29 | 2024-02-15 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), Gemini 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| WeirdML | 47.7% | 22.2% |
| LMArena Coding | 1489 | 1294 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| BigCodeBench Instruct | — | 43.8% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | — | 34% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 79.3% |
| MBPP+ | — | 74.6% |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| Cybench | 60% | 7.5% |
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| TheAgentCompany | — | 3.4% |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| BALROG | — | 21% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#125), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| ARC-AGI-2 | 13.6% | 0.8% |
| SimpleBench | 54.3% | 27.1% |
| LMArena Hard Prompts | 1462 | 1296 |
| DTBench | 83.2% | 59% |
| Epoch Capabilities Index | 146.84 | 131.73 |
| ForecastBench | 61.9 | 58.4 |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| LMCA | 38.8% | — |
| BIG-Bench Hard | — | 89.2% |
Math Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 32.3 (#216), Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 23.1% |
| Omni-MATH | 55.3% | 36.4% |
| LMArena Math | 1449 | 1315 |
| MATH Level 5 | 97.7% | 70.4% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | 82.3% | 57.2% |
| Humanity's Last Exam | 13.7% | 4.6% |
| MMLU-Pro | 86.9% | 73.7% |
| GPQA (HELM) | 68.6% | 53.4% |
| LMArena Expert | 1482 | 1279 |
| SimpleQA Verified | 30.7% | — |
| Confabulations | — | 13.5% |
| Vectara Hallucination Rate | 12% | — |
| MMLU | — | 86.9% |
Multimodal Gemini 1.5 Pro (May 2024) leads
Claude Sonnet 4.5: 34.8 (#89), Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | — | 1161 |
| Video-MME | — | 75% |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1425 | 1312 |
| LMArena Chinese | 1459 | 1331 |
| LMArena French | 1458 | 1302 |
| LMArena German | 1427 | 1286 |
| LMArena Japanese | 1390 | 1292 |
| LMArena Korean | 1403 | 1298 |
| LMArena Russian | 1437 | 1320 |
| LMArena Spanish | 1457 | 1311 |
Instruction Following Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 75.0 (#78), Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| IFEval | 85% | 83.7% |
| LMArena Instruction Following | 1459 | 1297 |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1476 | 1308 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | Claude Sonnet 4.5 | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1439 | 1319 |
| LMArena Creative Writing | 1442 | 1333 |
| WildBench | 85.4% | 81.3% |
| LMArena Multi-Turn | 1465 | 1296 |
| EQ-Bench Creative Writing | 1678 | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Gemini 1.5 Pro (May 2024)?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 32.1 on the Noometry Index.
Is Claude Sonnet 4.5 or Gemini 1.5 Pro (May 2024) better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 34.2 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and Gemini 1.5 Pro (May 2024) share?
33 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.