Model comparison
Claude 3 Opus vs Gemini 3 Pro
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 29.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Gemini 3 Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Pro leads 64.4 to 24.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 91.4% for Gemini 3 Pro.
Side by side
| Claude 3 Opus | Gemini 3 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.5 | 54.8 |
| Released | 2024-02-29 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 46 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Claude 3 Opus: 32.9 (#267), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| WeirdML | 19.2% | 69.9% |
| LMArena Coding | 1264 | 1481 |
| SWE-bench Verified | — | 72.9% |
| SWE-bench Verified (bash only) | — | 74.2% |
| LMArena WebDev | — | 1440 |
| SWE-bench Multilingual | — | 68.7% |
| GSO | — | 18.6% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,177 |
| AlgoTune | — | 1.83 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Gemini 3 Pro leads
Claude 3 Opus: 24.6 (#116), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| METR Time Horizons | 29.5% | 71% |
| Terminal-Bench | — | 69.4% |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| GDPval | — | 40.3% |
| Remote Labor Index | — | 1.3% |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Banking | — | 18% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| Cybench | 10% | — |
| DeepResearch Bench | — | 46.3% |
| BALROG | — | 58.1% |
| LMArena Search | — | 1207 |
| Vending-Bench 2 | — | 5,478 |
Reasoning Gemini 3 Pro leads
Claude 3 Opus: 14.6 (#324), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| SimpleBench | 23.5% | 76.4% |
| Chess Puzzles | 5% | 31% |
| EnigmaEval | 0.8% | 18.2% |
| LMArena Hard Prompts | 1245 | 1480 |
| Epoch Capabilities Index | 126.91 | 152.92 |
| ForecastBench | 58.4 | 61.2 |
| ARC-AGI-2 | — | 31.1% |
| Kagi LLM Benchmark | — | 80.1% |
| NYT Connections (extended) | — | 94.4% |
| ARC-AGI-1 | — | 75% |
| CritPt | — | 6.9% |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Gemini 3 Pro leads
Claude 3 Opus: 14.8 (#299), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 91.4% |
| LMArena Math | 1273 | 1476 |
| MathArena Final-Answer Competitions | — | 67% |
| ProofBench | — | 20% |
| Omni-MATH | — | 55.5% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 37.6% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge Gemini 3 Pro leads
Claude 3 Opus: 24.5 (#267), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 47.2% | 92.6% |
| LMArena Expert | 1223 | 1475 |
| Humanity's Last Exam | — | 37.5% |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 90.3% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 13.6% |
| GPQA (HELM) | — | 80.3% |
| MMLU | 84.6% | — |
Multimodal Gemini 3 Pro leads
Claude 3 Opus: 27.1 (#116), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1023 | 1305 |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| LMArena Document | — | 1434 |
Multilingual Gemini 3 Pro leads
Claude 3 Opus: 41.4 (#207), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1258 | 1474 |
| LMArena Chinese | 1248 | 1523 |
| LMArena French | 1275 | 1492 |
| LMArena German | 1258 | 1515 |
| LMArena Japanese | 1204 | 1510 |
| LMArena Korean | 1187 | 1448 |
| LMArena Russian | 1280 | 1493 |
| LMArena Spanish | 1246 | 1470 |
Instruction Following Gemini 3 Pro leads
Claude 3 Opus: 64.1 (#228), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1248 | 1458 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 87.7% |
Long Context Gemini 3 Pro leads
Claude 3 Opus: 38.2 (#202), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1259 | 1471 |
| CL-bench | — | 15.8% |
Writing & Preference Gemini 3 Pro leads
Claude 3 Opus: 47.2 (#213), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Claude 3 Opus | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1262 | 1479 |
| LMArena Creative Writing | 1235 | 1482 |
| LMArena Multi-Turn | 1275 | 1484 |
| EQ-Bench Creative Writing | — | 1525 |
| WildBench | — | 85.9% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Gemini 3 Pro?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Gemini 3 Pro better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Gemini 3 Pro share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemini 3 Pro has 67.