Model comparison
Claude 3 Opus vs Gemini 2.5 Pro
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 29.3 on the Noometry Index.
Last verified . 38 shared benchmarks.
GoogleSummary
- They share 38 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Gemini 2.5 Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 24.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 84.7% for Gemini 2.5 Pro.
Side by side
| Claude 3 Opus | Gemini 2.5 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.3 | 44.9 |
| Released | 2024-02-29 | 2025-03-25 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 46 | 78 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Claude 3 Opus: 32.4 (#261), Gemini 2.5 Pro: 42.8 (#86)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| WeirdML | 19.2% | 54% |
| LiveBench Coding | 38.6% | 85.9% |
| LMArena Coding | 1264 | 1452 |
| SWE-bench Verified | — | 57.6% |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| LMArena WebDev | — | 1227 |
| SciCode | — | 42.8% |
| GSO | — | 3.9% |
| BigCodeBench Instruct | 45.5% | — |
| BigCodeBench Complete | 57.4% | — |
| CadEval | — | 64% |
| ALE-Bench | — | 785.52 |
| AlgoTune | — | 1.51 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Gemini 2.5 Pro leads
Claude 3 Opus: 24.3 (#110), Gemini 2.5 Pro: 29.1 (#81)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| METR Time Horizons | 29.5% | 55.4% |
| Terminal-Bench | — | 32.6% |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| TheAgentCompany | — | 30.3% |
| τ²-bench Banking | — | 13.7% |
| Cybench | 10% | — |
| DeepResearch Bench | — | 42.8% |
| BALROG | — | 43.3% |
| LMArena Search | — | 1142 |
| Vending-Bench 2 | — | 573.64 |
Reasoning Gemini 2.5 Pro leads
Claude 3 Opus: 14.2 (#318), Gemini 2.5 Pro: 28.8 (#85)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| SimpleBench | 23.5% | 62.4% |
| Chess Puzzles | 5% | 20% |
| EnigmaEval | 0.8% | 5.6% |
| LiveBench Reasoning | 40.6% | 89.8% |
| LMArena Hard Prompts | 1246 | 1455 |
| DTBench | 61.6% | 82.4% |
| LiveBench Data Analysis | 57.9% | 79.9% |
| LMCA | 17% | 34.8% |
| Epoch Capabilities Index | 126.91 | 145.32 |
| ForecastBench | 58.4 | 61.3 |
| LiveBench | 49.2% | 82.3% |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 41% |
| CritPt | — | 2% |
| WinoGrande | 88.5% | — |
Math Gemini 2.5 Pro leads
Claude 3 Opus: 13.9 (#293), Gemini 2.5 Pro: 31.9 (#191)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 84.7% |
| LiveBench Math | 43.6% | 90.2% |
| LMArena Math | 1273 | 1450 |
| MATH Level 5 | 37.5% | 95.9% |
| FrontierMath (Tiers 1-3) | — | 24.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | — | 41.6% |
| FrontierMath (Feb 2025 set) | — | 14.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Pro leads
Claude 3 Opus: 24.5 (#262), Gemini 2.5 Pro: 55.8 (#41)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| GPQA Diamond | 47.2% | 85.3% |
| Confabulations | 22.7% | 10.6% |
| LMArena Expert | 1223 | 1452 |
| Humanity's Last Exam | — | 21.6% |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 86.3% |
| Vectara Hallucination Rate | — | 7% |
| GPQA (HELM) | — | 74.9% |
| MMLU | 84.6% | — |
Multimodal Gemini 2.5 Pro leads
Claude 3 Opus: 26.6 (#112), Gemini 2.5 Pro: 44.5 (#16)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | 1023 | 1263 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |
Multilingual Gemini 2.5 Pro leads
Claude 3 Opus: 41.6 (#202), Gemini 2.5 Pro: 55.5 (#30)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1258 | 1452 |
| LMArena Chinese | 1248 | 1507 |
| LMArena French | 1274 | 1473 |
| LMArena German | 1258 | 1487 |
| LMArena Japanese | 1204 | 1462 |
| LMArena Korean | 1187 | 1435 |
| LMArena Russian | 1280 | 1460 |
| LMArena Spanish | 1246 | 1473 |
Instruction Following Gemini 2.5 Pro leads
Claude 3 Opus: 64.3 (#223), Gemini 2.5 Pro: 75.2 (#71)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Instruction Following | 63.9% | 80.6% |
| LMArena Instruction Following | 1248 | 1436 |
| IFEval | — | 84% |
Long Context Gemini 2.5 Pro leads
Claude 3 Opus: 38.2 (#197), Gemini 2.5 Pro: 59.7 (#5)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1259 | 1449 |
| Fiction.LiveBench | — | 91.7% |
Writing & Preference Gemini 2.5 Pro leads
Claude 3 Opus: 47.4 (#208), Gemini 2.5 Pro: 63.9 (#60)
| Benchmark | Claude 3 Opus | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1262 | 1458 |
| LMArena Creative Writing | 1235 | 1453 |
| LMArena Multi-Turn | 1275 | 1453 |
| LiveBench Language | 50.4% | 67.8% |
| Short-Story Creative Writing | — | 83.8% |
| EQ-Bench Creative Writing | — | 1421 |
| WildBench | — | 85.7% |
Frequently asked questions
Is Claude 3 Opus better than Gemini 2.5 Pro?
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 29.3 on the Noometry Index.
Is Claude 3 Opus or Gemini 2.5 Pro better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 32.4 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Gemini 2.5 Pro share?
38 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemini 2.5 Pro has 78.