Model comparison
Claude Opus 4.7 vs Gemini 3 Pro
Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 54.8 on the Noometry Index.
Last verified . 46 shared benchmarks.
GoogleSummary
- They share 46 benchmarks with published results for both. Claude Opus 4.7 scores higher in 8 categories and Gemini 3 Pro in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.7 leads 66.7 to 49.9.
- The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 94.4% for Gemini 3 Pro.
Side by side
| Claude Opus 4.7 | Gemini 3 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 58.3 | 54.8 |
| Released | 2026-04-14 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 66 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.7 leads
Claude Opus 4.7: 59.6 (#13), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| SWE-bench Verified | 83.5% | 72.9% |
| LMArena WebDev | 1558 | 1440 |
| GSO | 44.1% | 18.6% |
| WeirdML | 76.4% | 69.9% |
| LMArena Coding | 1518 | 1481 |
| ALE-Bench | 1,323 | 1,177 |
| FrontierCode | 38.5% | — |
| SWE-bench Verified (bash only) | — | 74.2% |
| SWE-bench Multilingual | — | 68.7% |
| SciCode | 54.5% | — |
| MirrorCode | 31.1% | — |
| AlgoTune | — | 1.83 |
Agentic & Tool Use Claude Opus 4.7 leads
Claude Opus 4.7: 47.9 (#10), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| Terminal-Bench | 80.2% | 69.4% |
| τ²-bench Banking | 40.2% | 18% |
| LMArena Search | 1233 | 1207 |
| Vending-Bench 2 | 10,937 | 5,478 |
| APEX-Agents | 49.2% | — |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| OSWorld 2.0 | 18.2% | — |
| GDPval | — | 40.3% |
| Remote Labor Index | — | 1.3% |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| DeepResearch Bench | — | 46.3% |
| PostTrainBench | 28.6% | — |
| BALROG | — | 58.1% |
| ExploitBench | 26.5% | — |
| GBAEval | 43.8% | — |
| GDP.pdf | 21% | — |
| METR Time Horizons | — | 71% |
Reasoning Claude Opus 4.7 leads
Claude Opus 4.7: 53.8 (#29), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 75.8% | 31.1% |
| SimpleBench | 61.7% | 76.4% |
| Kagi LLM Benchmark | 80.7% | 80.1% |
| NYT Connections (extended) | 39% | 94.4% |
| ARC-AGI-1 | 93.5% | 75% |
| CritPt | 12% | 6.9% |
| Chess Puzzles | 30% | 31% |
| LMArena Hard Prompts | 1506 | 1480 |
| Epoch Capabilities Index | 156.25 | 152.92 |
| ForecastBench | 60.3 | 61.2 |
| EnigmaEval | — | 18.2% |
| Thematic Generalization | 72.8% | — |
| EBR-Bench | 19% | — |
| Mystery Game Puzzles | 28% | — |
| DTBench | 94.7% | — |
| LMCA | 52.2% | — |
Math Claude Opus 4.7 leads
Claude Opus 4.7: 66.7 (#26), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| MathArena Final-Answer Competitions | 73.6% | 67% |
| OTIS Mock AIME 2024-2025 | 97.8% | 91.4% |
| ProofBench | 54% | 20% |
| LMArena Math | 1499 | 1476 |
| FrontierMath (Feb 2025 set) | 43.8% | 37.6% |
| FrontierMath Tier 4 (v1) | 22.9% | 18.8% |
| FrontierMath (Tiers 1-3) | 70.2% | — |
| FrontierMath Tier 4 | 31.7% | — |
| Omni-MATH | — | 55.5% |
Knowledge Gemini 3 Pro leads
Claude Opus 4.7: 62.6 (#23), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 90.2% | 92.6% |
| Humanity's Last Exam | 36.2% | 37.5% |
| Vectara Hallucination Rate | 12% | 13.6% |
| LMArena Expert | 1521 | 1475 |
| SimpleQA Verified | 51.7% | — |
| MMLU-Pro | — | 90.3% |
| GPQA (HELM) | — | 80.3% |
Multimodal Gemini 3 Pro leads
Claude Opus 4.7: 41.2 (#38), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1316 | 1305 |
| LMArena Document | 1495 | 1434 |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| Blueprint-Bench 2 | 24.5% | — |
| Furniture Assembly | 33.3% | — |
Multilingual Too close to call
Claude Opus 4.7: 57.3 (#10), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1480 | 1474 |
| LMArena Chinese | 1531 | 1523 |
| LMArena French | 1503 | 1492 |
| LMArena German | 1495 | 1515 |
| LMArena Japanese | 1472 | 1510 |
| LMArena Korean | 1464 | 1448 |
| LMArena Russian | 1494 | 1493 |
| LMArena Spanish | 1495 | 1470 |
Instruction Following Claude Opus 4.7 leads
Claude Opus 4.7: 78.4 (#10), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1498 | 1458 |
| IFEval | — | 87.7% |
Long Context Claude Opus 4.7 leads
Claude Opus 4.7: 46.2 (#25), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1505 | 1471 |
| CL-bench | — | 15.8% |
Writing & Preference Claude Opus 4.7 leads
Claude Opus 4.7: 75.1 (#8), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Claude Opus 4.7 | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1490 | 1479 |
| LMArena Creative Writing | 1486 | 1482 |
| EQ-Bench Creative Writing | 1914 | 1525 |
| LMArena Multi-Turn | 1505 | 1484 |
| WildBench | — | 85.9% |
| EQ-Bench 4 | 1311 | — |
Frequently asked questions
Is Claude Opus 4.7 better than Gemini 3 Pro?
Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 54.8 on the Noometry Index.
Is Claude Opus 4.7 or Gemini 3 Pro better for coding?
Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 51.6 in the Noometry coding category.
How many benchmarks do Claude Opus 4.7 and Gemini 3 Pro share?
46 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Gemini 3 Pro has 67.