Model comparison
Gemini 1.5 Pro (May 2024) vs Grok 3
Grok 3 is the stronger model overall, scoring 39.9 to 32.1 on the Noometry Index.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 1 category and Grok 3 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 29.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 55.6% for Grok 3.
Side by side
| Gemini 1.5 Pro (May 2024) | Grok 3 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 32.1 | 39.9 |
| Released | 2024-02-15 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Grok 3: 41.9 (#115)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| WeirdML | 22.2% | 37.2% |
| LMArena Coding | 1294 | 1432 |
| Aider Polyglot | — | 53.3% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Grok 3 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Grok 3: 30.5 (#76)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| BALROG | 21% | 29.5% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
Reasoning Grok 3 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Grok 3: 13.7 (#333)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0% |
| SimpleBench | 27.1% | 36.1% |
| LMArena Hard Prompts | 1296 | 1434 |
| Epoch Capabilities Index | 131.73 | 138.33 |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 5.5% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Grok 3 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Grok 3: 38.0 (#145)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 55.6% |
| Omni-MATH | 36.4% | 46.4% |
| LMArena Math | 1315 | 1391 |
| MATH Level 5 | 70.4% | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Grok 3: 46.2 (#82)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| GPQA Diamond | 57.2% | 75.8% |
| MMLU-Pro | 73.7% | 78.8% |
| Confabulations | 13.5% | 14.2% |
| GPQA (HELM) | 53.4% | 65% |
| LMArena Expert | 1279 | 1421 |
| Humanity's Last Exam | 4.6% | — |
| Vectara Hallucination Rate | — | 5.8% |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Grok 3: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Grok 3 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Grok 3: 52.3 (#87)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| LMArena Non-English | 1312 | 1410 |
| LMArena Chinese | 1331 | 1448 |
| LMArena French | 1302 | 1460 |
| LMArena German | 1286 | 1431 |
| LMArena Japanese | 1292 | 1387 |
| LMArena Korean | 1298 | 1373 |
| LMArena Russian | 1320 | 1416 |
| LMArena Spanish | 1311 | 1417 |
Instruction Following Grok 3 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Grok 3: 75.0 (#73)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| IFEval | 83.7% | 88.4% |
| LMArena Instruction Following | 1297 | 1409 |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Grok 3: 38.7 (#192)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1308 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Grok 3 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Grok 3: 55.8 (#141)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok 3 |
|---|---|---|
| LMArena Text | 1319 | 1426 |
| LMArena Creative Writing | 1333 | 1414 |
| WildBench | 81.3% | 84.9% |
| LMArena Multi-Turn | 1296 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
| EQ-Bench Creative Writing | — | 1186 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.9 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Grok 3 share?
31 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Grok 3 has 40.