Model comparison
Claude 3 Opus vs Gemini 3.6 Flash
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 29.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Gemini 3.6 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 14.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 94.2% for Gemini 3.6 Flash.
Side by side
| Claude 3 Opus | Gemini 3.6 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.5 | 54.1 |
| Released | 2024-02-29 | 2026-07-21 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 46 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Claude 3 Opus: 32.9 (#267), Gemini 3.6 Flash: 50.0 (#48)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| WeirdML | 19.2% | 56.1% |
| LMArena Coding | 1264 | 1491 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| LMArena WebDev | — | 1538 |
| SciCode | — | 52.7% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 715.52 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Gemini 3.6 Flash leads
Claude 3 Opus: 24.6 (#116), Gemini 3.6 Flash: 32.3 (#65)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | — | 46.9% |
| Cybench | 10% | — |
| GDP.pdf | — | 14% |
| METR Time Horizons | 29.5% | — |
Reasoning Gemini 3.6 Flash leads
Claude 3 Opus: 14.6 (#324), Gemini 3.6 Flash: 58.8 (#22)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| Chess Puzzles | 5% | 43% |
| LMArena Hard Prompts | 1245 | 1485 |
| DTBench | 61.6% | 95.5% |
| LMCA | 17% | 44.9% |
| Epoch Capabilities Index | 126.91 | 154.25 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 89% |
| ARC-AGI-1 | — | 91.2% |
| CritPt | — | 10.6% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 30% |
| LiveBench Data Analysis | 57.9% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Gemini 3.6 Flash leads
Claude 3 Opus: 14.8 (#299), Gemini 3.6 Flash: 57.3 (#40)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 94.2% |
| LMArena Math | 1273 | 1505 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| ProofBench | — | 36% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Gemini 3.6 Flash leads
Claude 3 Opus: 24.5 (#267), Gemini 3.6 Flash: 67.8 (#8)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 47.2% | 94.1% |
| SimpleQA Verified | 12.6% | 66.2% |
| LMArena Expert | 1223 | 1488 |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Gemini 3.6 Flash leads
Claude 3 Opus: 27.1 (#116), Gemini 3.6 Flash: 38.5 (#64)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | 1023 | 1298 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |
Multilingual Gemini 3.6 Flash leads
Claude 3 Opus: 41.4 (#207), Gemini 3.6 Flash: 56.5 (#19)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1258 | 1469 |
| LMArena Chinese | 1248 | 1531 |
| LMArena French | 1275 | 1504 |
| LMArena German | 1258 | 1478 |
| LMArena Japanese | 1204 | 1476 |
| LMArena Korean | 1187 | 1431 |
| LMArena Russian | 1280 | 1487 |
| LMArena Spanish | 1246 | 1475 |
Instruction Following Gemini 3.6 Flash leads
Claude 3 Opus: 64.1 (#228), Gemini 3.6 Flash: 77.0 (#33)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1248 | 1466 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Gemini 3.6 Flash leads
Claude 3 Opus: 38.2 (#202), Gemini 3.6 Flash: 45.1 (#50)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1259 | 1474 |
Writing & Preference Gemini 3.6 Flash leads
Claude 3 Opus: 47.2 (#213), Gemini 3.6 Flash: 68.2 (#27)
| Benchmark | Claude 3 Opus | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1262 | 1479 |
| LMArena Creative Writing | 1235 | 1465 |
| LMArena Multi-Turn | 1275 | 1481 |
| EQ-Bench Creative Writing | — | 1604 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Gemini 3.6 Flash?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Gemini 3.6 Flash better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Gemini 3.6 Flash share?
26 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemini 3.6 Flash has 46.