Model comparison
Claude Opus 4.5 vs Gemini 3 Pro
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 50.5 on the Noometry Index.
Last verified . 59 shared benchmarks.
GoogleSummary
- They share 59 benchmarks with published results for both. Claude Opus 4.5 scores higher in 5 categories and Gemini 3 Pro in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 3 Pro leads 57.6 to 31.4.
- The biggest single-benchmark swing is VPCT: 40% for Claude Opus 4.5 and 91% for Gemini 3 Pro.
Side by side
| Claude Opus 4.5 | Gemini 3 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 50.5 | 54.8 |
| Released | 2025-11-01 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 69 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.5 leads
Claude Opus 4.5: 54.8 (#27), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| SWE-bench Verified | 76.7% | 72.9% |
| SWE-bench Verified (bash only) | 76.8% | 74.2% |
| LMArena WebDev | 1494 | 1440 |
| SWE-bench Multilingual | 70.7% | 68.7% |
| GSO | 26.5% | 18.6% |
| WeirdML | 63.7% | 69.9% |
| LMArena Coding | 1504 | 1481 |
| ALE-Bench | 1,025 | 1,177 |
| AlgoTune | 1.77 | 1.83 |
Agentic & Tool Use Claude Opus 4.5 leads
Claude Opus 4.5: 47.3 (#12), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| Terminal-Bench | 63.1% | 69.4% |
| Berkeley Function Calling Leaderboard | 77.5% | 72.5% |
| GDPval | 45.5% | 40.3% |
| Remote Labor Index | 3.8% | 1.3% |
| τ²-bench Airline | 84% | 80.5% |
| τ²-bench Banking | 24.7% | 18% |
| τ²-bench Retail | 79.6% | 75.9% |
| τ²-bench Telecom | 92.3% | 91% |
| DeepResearch Bench | 54.8% | 46.3% |
| BALROG | 43.5% | 58.1% |
| LMArena Search | 1180 | 1207 |
| METR Time Horizons | 75% | 71% |
| Vending-Bench 2 | 4,967 | 5,478 |
| Cybench | 82% | — |
| OSWorld | 66.3% | — |
Reasoning Gemini 3 Pro leads
Claude Opus 4.5: 42.6 (#51), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 37.6% | 31.1% |
| SimpleBench | 62% | 76.4% |
| Kagi LLM Benchmark | 80.2% | 80.1% |
| NYT Connections (extended) | 52.5% | 94.4% |
| ARC-AGI-1 | 80% | 75% |
| Chess Puzzles | 12% | 31% |
| EnigmaEval | 11.9% | 18.2% |
| LMArena Hard Prompts | 1476 | 1480 |
| Epoch Capabilities Index | 150.09 | 152.92 |
| ForecastBench | 60.7 | 61.2 |
| CritPt | — | 6.9% |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 22% | — |
| DTBench | 89.9% | — |
| LMCA | 44.5% | — |
Math Gemini 3 Pro leads
Claude Opus 4.5: 38.6 (#132), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.1% | 91.4% |
| ProofBench | 36% | 20% |
| LMArena Math | 1463 | 1476 |
| FrontierMath (Feb 2025 set) | 20.7% | 37.6% |
| FrontierMath Tier 4 (v1) | 4.2% | 18.8% |
| FrontierMath (Tiers 1-3) | 34.4% | — |
| FrontierMath Tier 4 | 4.9% | — |
| MathArena Final-Answer Competitions | — | 67% |
| Omni-MATH | — | 55.5% |
Knowledge Gemini 3 Pro leads
Claude Opus 4.5: 56.5 (#44), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 86% | 92.6% |
| Humanity's Last Exam | 25.2% | 37.5% |
| Vectara Hallucination Rate | 10.9% | 13.6% |
| LMArena Expert | 1487 | 1475 |
| SimpleQA Verified | 45.7% | — |
| MMLU-Pro | — | 90.3% |
| GPQA (HELM) | — | 80.3% |
Multimodal Gemini 3 Pro leads
Claude Opus 4.5: 31.4 (#107), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| GeoBench | 75% | 84% |
| VPCT | 40% | 91% |
| LMArena Document | 1462 | 1434 |
| LMArena Vision | — | 1305 |
| Furniture Assembly | 28.3% | — |
Multilingual Gemini 3 Pro leads
Claude Opus 4.5: 54.3 (#47), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1438 | 1474 |
| LMArena Chinese | 1470 | 1523 |
| LMArena French | 1471 | 1492 |
| LMArena German | 1449 | 1515 |
| LMArena Japanese | 1416 | 1510 |
| LMArena Korean | 1424 | 1448 |
| LMArena Russian | 1447 | 1493 |
| LMArena Spanish | 1458 | 1470 |
Instruction Following Claude Opus 4.5 leads
Claude Opus 4.5: 77.5 (#19), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1478 | 1458 |
| IFEval | — | 87.7% |
Long Context Claude Opus 4.5 leads
Claude Opus 4.5: 46.5 (#22), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| CL-bench | 21.1% | 15.8% |
| LMArena Longer Query | 1480 | 1471 |
Writing & Preference Claude Opus 4.5 leads
Claude Opus 4.5: 68.1 (#28), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Claude Opus 4.5 | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1451 | 1479 |
| LMArena Creative Writing | 1445 | 1482 |
| EQ-Bench Creative Writing | 1687 | 1525 |
| LMArena Multi-Turn | 1466 | 1484 |
| WildBench | — | 85.9% |
Frequently asked questions
Is Claude Opus 4.5 better than Gemini 3 Pro?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 50.5 on the Noometry Index.
Is Claude Opus 4.5 or Gemini 3 Pro better for coding?
Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 51.6 in the Noometry coding category.
How many benchmarks do Claude Opus 4.5 and Gemini 3 Pro share?
59 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Gemini 3 Pro has 67.