Model comparison
Claude Opus 4.1 vs Gemini 3 Pro
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 41.0 on the Noometry Index.
Last verified . 39 shared benchmarks.
GoogleSummary
- They share 39 benchmarks with published results for both. Claude Opus 4.1 scores higher in 1 category and Gemini 3 Pro in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 3 Pro leads 57.6 to 26.8.
- The biggest single-benchmark swing is VPCT: 35% for Claude Opus 4.1 and 91% for Gemini 3 Pro.
Side by side
| Claude Opus 4.1 | Gemini 3 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 41.0 | 54.8 |
| Released | 2025-08-05 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 32K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $75 | — |
| Results tracked | 48 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Claude Opus 4.1: 44.4 (#73), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| SWE-bench Verified | 73.3% | 72.9% |
| LMArena WebDev | 1390 | 1440 |
| WeirdML | 45.9% | 69.9% |
| LMArena Coding | 1479 | 1481 |
| ALE-Bench | 674.77 | 1,177 |
| AlgoTune | 1.34 | 1.83 |
| SWE-bench Verified (bash only) | — | 74.2% |
| SWE-bench Multilingual | — | 68.7% |
| GSO | — | 18.6% |
Agentic & Tool Use Gemini 3 Pro leads
Claude Opus 4.1: 35.0 (#41), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| Terminal-Bench | 38% | 69.4% |
| GDPval | 43.6% | 40.3% |
| DeepResearch Bench | 48.3% | 46.3% |
| LMArena Search | 1148 | 1207 |
| METR Time Horizons | 66.8% | 71% |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| Remote Labor Index | — | 1.3% |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Banking | — | 18% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| Cybench | 42% | — |
| BALROG | — | 58.1% |
| Vending-Bench 2 | — | 5,478 |
Reasoning Gemini 3 Pro leads
Claude Opus 4.1: 32.2 (#76), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| SimpleBench | 60% | 76.4% |
| Chess Puzzles | 7% | 31% |
| EnigmaEval | 7.2% | 18.2% |
| LMArena Hard Prompts | 1443 | 1480 |
| Epoch Capabilities Index | 144.12 | 152.92 |
| ForecastBench | 62 | 61.2 |
| ARC-AGI-2 | — | 31.1% |
| Kagi LLM Benchmark | — | 80.1% |
| NYT Connections (extended) | — | 94.4% |
| ARC-AGI-1 | — | 75% |
| CritPt | — | 6.9% |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 80% | — |
| LMCA | 37.1% | — |
Math Gemini 3 Pro leads
Claude Opus 4.1: 22.3 (#277), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 91.4% |
| LMArena Math | 1431 | 1476 |
| FrontierMath (Feb 2025 set) | 7.2% | 37.6% |
| FrontierMath Tier 4 (v1) | 4.2% | 18.8% |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| MathArena Final-Answer Competitions | — | 67% |
| ProofBench | — | 20% |
| Omni-MATH | — | 55.5% |
Knowledge Gemini 3 Pro leads
Claude Opus 4.1: 42.0 (#101), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 77.3% | 92.6% |
| Humanity's Last Exam | 11.5% | 37.5% |
| Vectara Hallucination Rate | 11.8% | 13.6% |
| LMArena Expert | 1439 | 1475 |
| MMLU-Pro | — | 90.3% |
| Confabulations | 17.1% | — |
| GPQA (HELM) | — | 80.3% |
Multimodal Gemini 3 Pro leads
Claude Opus 4.1: 26.8 (#119), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| VPCT | 35% | 91% |
| LMArena Vision | — | 1305 |
| GeoBench | — | 84% |
| LMArena Document | — | 1434 |
Multilingual Gemini 3 Pro leads
Claude Opus 4.1: 52.0 (#95), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1405 | 1474 |
| LMArena Chinese | 1427 | 1523 |
| LMArena French | 1431 | 1492 |
| LMArena German | 1413 | 1515 |
| LMArena Japanese | 1378 | 1510 |
| LMArena Korean | 1380 | 1448 |
| LMArena Russian | 1422 | 1493 |
| LMArena Spanish | 1448 | 1470 |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1435 | 1458 |
| IFEval | — | 87.7% |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1455 | 1471 |
| CL-bench | — | 15.8% |
Writing & Preference Gemini 3 Pro leads
Claude Opus 4.1: 62.4 (#74), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Claude Opus 4.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1419 | 1479 |
| LMArena Creative Writing | 1412 | 1482 |
| LMArena Multi-Turn | 1444 | 1484 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1525 |
| WildBench | — | 85.9% |
Frequently asked questions
Is Claude Opus 4.1 better than Gemini 3 Pro?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 41.0 on the Noometry Index.
Is Claude Opus 4.1 or Gemini 3 Pro better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 44.4 in the Noometry coding category.
How many benchmarks do Claude Opus 4.1 and Gemini 3 Pro share?
39 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Gemini 3 Pro has 67.