Model comparison
Claude Opus 5 vs Gemini 3 Pro
Claude Opus 5 is the stronger model overall, scoring 67.8 to 54.8 on the Noometry Index.
Last verified . 36 shared benchmarks.
GoogleSummary
- They share 36 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and Gemini 3 Pro in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.2 to 49.9.
- The biggest single-benchmark swing is ProofBench: 99% for Claude Opus 5 and 20% for Gemini 3 Pro.
Side by side
| Claude Opus 5 | Gemini 3 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 67.8 | 54.8 |
| Released | 2026-07-24 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 57 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| LMArena WebDev | 1691 | 1440 |
| WeirdML | 91.8% | 69.9% |
| LMArena Coding | 1534 | 1481 |
| ALE-Bench | 2,165 | 1,177 |
| SWE-bench Verified | — | 72.9% |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| SWE-bench Verified (bash only) | — | 74.2% |
| CursorBench | 46.6% | — |
| SWE-bench Multilingual | — | 68.7% |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| GSO | — | 18.6% |
| AlgoTune | — | 1.83 |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| τ²-bench Banking | 48.7% | 18% |
| BALROG | 63.4% | 58.1% |
| Vending-Bench 2 | 11,182 | 5,478 |
| Terminal-Bench | — | 69.4% |
| APEX-Agents | 65.8% | — |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| OSWorld 2.0 | 31.4% | — |
| GDPval | — | 40.3% |
| Remote Labor Index | — | 1.3% |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| DeepResearch Bench | — | 46.3% |
| PostTrainBench | 35% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 71% |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 90.4% | 31.1% |
| SimpleBench | 80.6% | 76.4% |
| NYT Connections (extended) | 94.3% | 94.4% |
| ARC-AGI-1 | 97.5% | 75% |
| CritPt | 29.1% | 6.9% |
| Chess Puzzles | 42% | 31% |
| LMArena Hard Prompts | 1526 | 1480 |
| Epoch Capabilities Index | 162.78 | 152.92 |
| Kagi LLM Benchmark | — | 80.1% |
| EnigmaEval | — | 18.2% |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| DTBench | 97.9% | — |
| LMCA | 64.5% | — |
| Bench to the Future 3 | 0.12 | — |
| ForecastBench | — | 61.2 |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 91.4% |
| ProofBench | 99% | 20% |
| LMArena Math | 1531 | 1476 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| MathArena Final-Answer Competitions | — | 67% |
| Omni-MATH | — | 55.5% |
| FrontierMath (Feb 2025 set) | — | 37.6% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 93.9% | 92.6% |
| LMArena Expert | 1557 | 1475 |
| Humanity's Last Exam | — | 37.5% |
| SimpleQA Verified | 59.9% | — |
| MMLU-Pro | — | 90.3% |
| Vectara Hallucination Rate | — | 13.6% |
| GPQA (HELM) | — | 80.3% |
Multimodal Gemini 3 Pro leads
Claude Opus 5: 50.8 (#8), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1319 | 1305 |
| LMArena Document | 1516 | 1434 |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1501 | 1474 |
| LMArena Chinese | 1574 | 1523 |
| LMArena French | 1519 | 1492 |
| LMArena German | 1524 | 1515 |
| LMArena Japanese | 1516 | 1510 |
| LMArena Korean | 1521 | 1448 |
| LMArena Russian | 1507 | 1493 |
| LMArena Spanish | 1519 | 1470 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1517 | 1458 |
| IFEval | — | 87.7% |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1515 | 1471 |
| CL-bench | — | 15.8% |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Claude Opus 5 | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1507 | 1479 |
| LMArena Creative Writing | 1491 | 1482 |
| EQ-Bench Creative Writing | 2133 | 1525 |
| LMArena Multi-Turn | 1499 | 1484 |
| WildBench | — | 85.9% |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than Gemini 3 Pro?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 54.8 on the Noometry Index.
Is Claude Opus 5 or Gemini 3 Pro better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 51.6 in the Noometry coding category.
How many benchmarks do Claude Opus 5 and Gemini 3 Pro share?
36 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Gemini 3 Pro has 67.