Model comparison
Gemini 3 Pro vs Grok 4.7
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 53.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 3 Pro scores higher in 7 categories and Grok 4.7 in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 3 Pro leads 57.6 to 35.5.
- The biggest single-benchmark swing is NYT Connections (extended): 94.4% for Gemini 3 Pro and 76.8% for Grok 4.7.
Side by side
| Gemini 3 Pro | Grok 4.7 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 54.8 | 53.1 |
| Released | 2025-11-18 | 2026-09-21 |
| Weights | Proprietary | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 67 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Gemini 3 Pro: 51.6 (#39), Grok 4.7: 58.0 (#18)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| LMArena WebDev | 1440 | 1639 |
| LMArena Coding | 1481 | 1427 |
| SWE-bench Verified | 72.9% | — |
| FrontierCode | — | 47.6% |
| SWE-bench Verified (bash only) | 74.2% | — |
| CursorBench | — | 46.3% |
| SWE-bench Multilingual | 68.7% | — |
| FrontierSWE | — | 29.5% |
| SciCode | — | 57.8% |
| GSO | 18.6% | — |
| WeirdML | 69.9% | — |
| ALE-Bench | 1,177 | — |
| AlgoTune | 1.83 | — |
Agentic & Tool Use Gemini 3 Pro leads
Gemini 3 Pro: 40.6 (#23), Grok 4.7: 36.7 (#37)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| Vending-Bench 2 | 5,478 | 10,537 |
| Terminal-Bench | 69.4% | — |
| APEX-Agents | — | 54.6% |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| GDP.pdf | — | 22.8% |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
Reasoning Gemini 3 Pro leads
Gemini 3 Pro: 52.5 (#31), Grok 4.7: 49.1 (#40)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| NYT Connections (extended) | 94.4% | 76.8% |
| CritPt | 6.9% | 18% |
| Chess Puzzles | 31% | 38% |
| LMArena Hard Prompts | 1480 | 1413 |
| Epoch Capabilities Index | 152.92 | 153.53 |
| ARC-AGI-2 | 31.1% | — |
| SimpleBench | 76.4% | — |
| Kagi LLM Benchmark | 80.1% | — |
| ARC-AGI-1 | 75% | — |
| EnigmaEval | 18.2% | — |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 96% |
| LMCA | — | 49.4% |
| ForecastBench | 61.2 | — |
Math Grok 4.7 leads
Gemini 3 Pro: 49.9 (#59), Grok 4.7: 57.8 (#39)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 98.1% |
| ProofBench | 20% | 34% |
| LMArena Math | 1476 | 1407 |
| FrontierMath (Tiers 1-3) | — | 53% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | 67% | — |
| Omni-MATH | 55.5% | — |
| FrontierMath (Feb 2025 set) | 37.6% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge Gemini 3 Pro leads
Gemini 3 Pro: 64.4 (#16), Grok 4.7: 62.8 (#22)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 92.6% | 92.7% |
| LMArena Expert | 1475 | 1422 |
| Humanity's Last Exam | 37.5% | — |
| SimpleQA Verified | — | 56% |
| MMLU-Pro | 90.3% | — |
| Vectara Hallucination Rate | 13.6% | — |
| GPQA (HELM) | 80.3% | — |
Multimodal Gemini 3 Pro leads
Gemini 3 Pro: 57.6 (#2), Grok 4.7: 35.5 (#87)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| LMArena Vision | 1305 | 1228 |
| GeoBench | 84% | — |
| VPCT | 91% | — |
| Blueprint-Bench 2 | — | 32.5% |
| Furniture Assembly | — | 20.8% |
| LMArena Document | 1434 | — |
Multilingual Gemini 3 Pro leads
Gemini 3 Pro: 56.9 (#16), Grok 4.7: 50.8 (#116)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1474 | 1389 |
| LMArena Chinese | 1523 | 1455 |
| LMArena French | 1492 | 1455 |
| LMArena Russian | 1493 | 1397 |
| LMArena Spanish | 1470 | 1400 |
| LMArena German | 1515 | — |
| LMArena Japanese | 1510 | — |
| LMArena Korean | 1448 | — |
Instruction Following Gemini 3 Pro leads
Gemini 3 Pro: 76.3 (#45), Grok 4.7: 74.1 (#105)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1458 | 1404 |
| IFEval | 87.7% | — |
Long Context Too close to call
Gemini 3 Pro: 44.0 (#79), Grok 4.7: 43.1 (#104)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1471 | 1413 |
| CL-bench | 15.8% | — |
Writing & Preference Grok 4.7 leads
Gemini 3 Pro: 66.4 (#35), Grok 4.7: 70.0 (#24)
| Benchmark | Gemini 3 Pro | Grok 4.7 |
|---|---|---|
| LMArena Text | 1479 | 1399 |
| LMArena Creative Writing | 1482 | 1391 |
| EQ-Bench Creative Writing | 1525 | 2007 |
| LMArena Multi-Turn | 1484 | 1393 |
| WildBench | 85.9% | — |
Frequently asked questions
Is Gemini 3 Pro better than Grok 4.7?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 53.1 on the Noometry Index.
Is Gemini 3 Pro or Grok 4.7 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 51.6 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and Grok 4.7 share?
25 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and Grok 4.7 has 39.