Model comparison
Claude 3 Opus vs Gemini 3.7 Flash
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 29.5 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Gemini 3.7 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 14.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 97.2% for Gemini 3.7 Flash.
Side by side
| Claude 3 Opus | Gemini 3.7 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.5 | 59.8 |
| Released | 2024-02-29 | 2026-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 46 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Claude 3 Opus: 32.9 (#267), Gemini 3.7 Flash: 56.2 (#22)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| LMArena Coding | 1264 | 1497 |
| DeepSWE | — | 65.5% |
| FrontierCode | — | 43.6% |
| LMArena WebDev | — | 1592 |
| FrontierSWE | — | 20.3% |
| SciCode | — | 59.8% |
| WeirdML | 19.2% | — |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 904.3 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Gemini 3.7 Flash leads
Claude 3 Opus: 24.6 (#116), Gemini 3.7 Flash: 42.1 (#19)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | — | 67.8% |
| Remote Labor Index | — | 5% |
| Cybench | 10% | — |
| GDP.pdf | — | 23.8% |
| METR Time Horizons | 29.5% | — |
Reasoning Gemini 3.7 Flash leads
Claude 3 Opus: 14.6 (#324), Gemini 3.7 Flash: 70.0 (#15)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| Chess Puzzles | 5% | 47% |
| LMArena Hard Prompts | 1245 | 1494 |
| DTBench | 61.6% | 96.8% |
| LMCA | 17% | 50.4% |
| Epoch Capabilities Index | 126.91 | 157.27 |
| ARC-AGI-2 | — | 84.6% |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 94% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 14.3% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 37% |
| LiveBench Data Analysis | 57.9% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Gemini 3.7 Flash leads
Claude 3 Opus: 14.8 (#299), Gemini 3.7 Flash: 69.6 (#23)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 97.2% |
| LMArena Math | 1273 | 1507 |
| FrontierMath (Tiers 1-3) | — | 71.6% |
| FrontierMath Tier 4 | — | 36.6% |
| ProofBench | — | 58% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Gemini 3.7 Flash leads
Claude 3 Opus: 24.5 (#267), Gemini 3.7 Flash: 69.7 (#5)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 47.2% | 94.8% |
| SimpleQA Verified | 12.6% | 69.2% |
| LMArena Expert | 1223 | 1508 |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Gemini 3.7 Flash leads
Claude 3 Opus: 27.1 (#116), Gemini 3.7 Flash: 37.3 (#73)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1023 | 1316 |
| Furniture Assembly | — | 26.7% |
Multilingual Gemini 3.7 Flash leads
Claude 3 Opus: 41.4 (#207), Gemini 3.7 Flash: 57.6 (#7)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1258 | 1484 |
| LMArena Chinese | 1248 | 1548 |
| LMArena French | 1275 | 1505 |
| LMArena German | 1258 | 1498 |
| LMArena Japanese | 1204 | 1512 |
| LMArena Korean | 1187 | 1483 |
| LMArena Russian | 1280 | 1516 |
| LMArena Spanish | 1246 | 1503 |
Instruction Following Gemini 3.7 Flash leads
Claude 3 Opus: 64.1 (#228), Gemini 3.7 Flash: 77.7 (#15)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1248 | 1483 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Gemini 3.7 Flash leads
Claude 3 Opus: 38.2 (#202), Gemini 3.7 Flash: 45.7 (#30)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1259 | 1492 |
Writing & Preference Gemini 3.7 Flash leads
Claude 3 Opus: 47.2 (#213), Gemini 3.7 Flash: 71.2 (#20)
| Benchmark | Claude 3 Opus | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1262 | 1486 |
| LMArena Creative Writing | 1235 | 1490 |
| LMArena Multi-Turn | 1275 | 1489 |
| EQ-Bench Creative Writing | — | 1723 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Gemini 3.7 Flash?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Gemini 3.7 Flash better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Gemini 3.7 Flash share?
25 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemini 3.7 Flash has 44.