Model comparison
Gemini 1.5 Pro (May 2024) vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 32.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Grok 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 12.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 99.2% for Grok 4.6.
Side by side
| Gemini 1.5 Pro (May 2024) | Grok 4.6 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 32.1 | 56.9 |
| Released | 2024-02-15 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 45 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Grok 4.6: 58.5 (#16)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| WeirdML | 22.2% | 67.3% |
| LMArena Coding | 1294 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Grok 4.6: 39.4 (#27)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Grok 4.6: 61.4 (#20)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 67.1% |
| SimpleBench | 27.1% | 75.9% |
| LMArena Hard Prompts | 1296 | 1447 |
| DTBench | 59% | 97.3% |
| Epoch Capabilities Index | 131.73 | 156.44 |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| LMCA | — | 48.5% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Grok 4.6: 67.0 (#24)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 99.2% |
| LMArena Math | 1315 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Grok 4.6: 63.3 (#20)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 57.2% | 94% |
| LMArena Expert | 1279 | 1467 |
| Humanity's Last Exam | 4.6% | — |
| SimpleQA Verified | — | 49.3% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), Grok 4.6: 43.6 (#23)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1161 | 1263 |
| Video-MME | 75% | — |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Grok 4.6: 53.0 (#74)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1312 | 1420 |
| LMArena Chinese | 1331 | 1480 |
| LMArena French | 1302 | 1461 |
| LMArena German | 1286 | 1431 |
| LMArena Japanese | 1292 | 1376 |
| LMArena Korean | 1298 | 1397 |
| LMArena Russian | 1320 | 1422 |
| LMArena Spanish | 1311 | 1404 |
Instruction Following Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Grok 4.6: 75.4 (#63)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1431 |
| IFEval | 83.7% | — |
Long Context Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Grok 4.6: 44.5 (#66)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1308 | 1454 |
Writing & Preference Grok 4.6 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Grok 4.6: 62.3 (#80)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 4.6 |
|---|---|---|
| LMArena Text | 1319 | 1428 |
| LMArena Creative Writing | 1333 | 1428 |
| LMArena Multi-Turn | 1296 | 1425 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Grok 4.6 share?
25 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Grok 4.6 has 49.