Model comparison
Claude 3 Opus vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 29.5 on the Noometry Index.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Gemini 3.1 Pro Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 14.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 95.6% for Gemini 3.1 Pro Preview.
Side by side
| Claude 3 Opus | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.5 | 56.7 |
| Released | 2024-02-29 | 2026-02-19 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $12 |
| Results tracked | 46 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Claude 3 Opus: 32.9 (#267), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| WeirdML | 19.2% | 72.1% |
| LMArena Coding | 1264 | 1484 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| MirrorCode | — | 8.9% |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Gemini 3.1 Pro Preview leads
Claude 3 Opus: 24.6 (#116), Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| METR Time Horizons | 29.5% | 77% |
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| τ²-bench Banking | — | 26% |
| Cybench | 10% | — |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
Claude 3 Opus: 14.6 (#324), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| SimpleBench | 23.5% | 79.6% |
| Chess Puzzles | 5% | 55% |
| EnigmaEval | 0.8% | 36.8% |
| LMArena Hard Prompts | 1245 | 1485 |
| DTBench | 61.6% | 97.1% |
| LMCA | 17% | 53.8% |
| Epoch Capabilities Index | 126.91 | 154.77 |
| ForecastBench | 58.4 | 59 |
| ARC-AGI-2 | — | 77.1% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 34% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Gemini 3.1 Pro Preview leads
Claude 3 Opus: 14.8 (#299), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 95.6% |
| LMArena Math | 1273 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| ProofBench | — | 26% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Gemini 3.1 Pro Preview leads
Claude 3 Opus: 24.5 (#267), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 47.2% | 94.4% |
| SimpleQA Verified | 12.6% | 73.5% |
| LMArena Expert | 1223 | 1485 |
| Humanity's Last Exam | — | 46.4% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 10.4% |
| MMLU | 84.6% | — |
Multimodal Gemini 3.1 Pro Preview leads
Claude 3 Opus: 27.1 (#116), Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 1023 | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
Claude 3 Opus: 41.4 (#207), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1258 | 1477 |
| LMArena Chinese | 1248 | 1529 |
| LMArena French | 1275 | 1487 |
| LMArena German | 1258 | 1491 |
| LMArena Japanese | 1204 | 1493 |
| LMArena Korean | 1187 | 1455 |
| LMArena Russian | 1280 | 1498 |
| LMArena Spanish | 1246 | 1479 |
Instruction Following Gemini 3.1 Pro Preview leads
Claude 3 Opus: 64.1 (#228), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1248 | 1466 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Gemini 3.1 Pro Preview leads
Claude 3 Opus: 38.2 (#202), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1259 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Gemini 3.1 Pro Preview leads
Claude 3 Opus: 47.2 (#213), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | Claude 3 Opus | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1262 | 1481 |
| LMArena Creative Writing | 1235 | 1482 |
| LMArena Multi-Turn | 1275 | 1488 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Gemini 3.1 Pro Preview share?
30 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemini 3.1 Pro Preview has 71.