Model comparison
Gemini 1.5 Pro (May 2024) vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.0 to 31.9 on the Noometry Index.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Grok-3 mini in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.3 to 29.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 77.8% for Grok-3 mini.
Side by side
| Gemini 1.5 Pro (May 2024) | Grok-3 mini | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 31.9 | 41.0 |
| Released | 2024-02-15 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 33.8 (#239), Grok-3 mini: 40.4 (#126)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| WeirdML | 22.2% | 42.6% |
| LMArena Coding | 1294 | 1380 |
| Aider Polyglot | — | 49.3% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.8 (#137), Grok-3 mini: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 12.3 (#332), Grok-3 mini: 13.8 (#323)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0.4% |
| LMArena Hard Prompts | 1296 | 1374 |
| Epoch Capabilities Index | 131.73 | 140.35 |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 24.4 (#260), Grok-3 mini: 40.3 (#78)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 77.8% |
| Omni-MATH | 36.4% | 31.8% |
| LMArena Math | 1315 | 1386 |
| MATH Level 5 | 70.4% | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 29.3 (#228), Grok-3 mini: 46.3 (#75)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 57.2% | 76.3% |
| MMLU-Pro | 73.7% | 79.9% |
| Confabulations | 13.5% | 10.8% |
| GPQA (HELM) | 53.4% | 67.5% |
| LMArena Expert | 1279 | 1395 |
| Humanity's Last Exam | 4.6% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.2 (#72), Grok-3 mini: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 45.5 (#169), Grok-3 mini: 48.3 (#141)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1312 | 1352 |
| LMArena Chinese | 1331 | 1387 |
| LMArena French | 1301 | 1357 |
| LMArena German | 1286 | 1350 |
| LMArena Japanese | 1292 | 1343 |
| LMArena Korean | 1298 | 1336 |
| LMArena Russian | 1320 | 1352 |
| LMArena Spanish | 1310 | 1379 |
Instruction Following Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 68.8 (#180), Grok-3 mini: 78.7 (#8)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| IFEval | 83.7% | 95.1% |
| LMArena Instruction Following | 1297 | 1356 |
Long Context Grok-3 mini leads
Gemini 1.5 Pro (May 2024): 39.7 (#164), Grok-3 mini: 41.0 (#142)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1308 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Too close to call
Gemini 1.5 Pro (May 2024): 52.5 (#167), Grok-3 mini: 52.7 (#163)
| Benchmark | Gemini 1.5 Pro (May 2024) | Grok-3 mini |
|---|---|---|
| LMArena Text | 1319 | 1370 |
| LMArena Creative Writing | 1333 | 1342 |
| WildBench | 81.3% | 65.1% |
| LMArena Multi-Turn | 1296 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.0 to 31.9 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.4 versus 33.8 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Grok-3 mini share?
29 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Grok-3 mini has 35.