Model comparison
Gemini 2.0 Pro vs Grok 4
Grok 4 is the stronger model overall, scoring 48.1 to 39.1 on the Noometry Index.
Last verified . 5 shared benchmarks.
GoogleSummary
- They share 5 benchmarks with published results for both. Gemini 2.0 Pro scores higher in 0 categories and Grok 4 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 29.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 41.7% for Gemini 2.0 Pro and 94.4% for Grok 4.
Side by side
| Gemini 2.0 Pro | Grok 4 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 39.1 | 48.1 |
| Released | 2025-02-05 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Gemini 2.0 Pro: 37.8 (#187), Grok 4: 50.3 (#46)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| Aider Polyglot | 35.6% | 79.6% |
| WeirdML | — | 45.7% |
| LiveBench Coding | 63.5% | — |
| LMArena Coding | — | 1408 |
Agentic & Tool Use Not comparable
Gemini 2.0 Pro: —, Grok 4: 32.3 (#68)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Grok 4 leads
Gemini 2.0 Pro: 22.3 (#198), Grok 4: 36.7 (#65)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| Epoch Capabilities Index | 135.06 | 146.44 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| EnigmaEval | 0.7% | — |
| LiveBench Reasoning | 60.1% | — |
| LMArena Hard Prompts | — | 1409 |
| LiveBench Data Analysis | 68% | — |
| ForecastBench | — | 60.9 |
| LiveBench | 65.1% | — |
Math Grok 4 leads
Gemini 2.0 Pro: 39.7 (#100), Grok 4: 48.4 (#64)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 84% |
| Omni-MATH | — | 60.3% |
| LiveBench Math | 71% | — |
| LMArena Math | — | 1422 |
| MATH Level 5 | 83.5% | — |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Grok 4 leads
Gemini 2.0 Pro: 36.5 (#167), Grok 4: 53.8 (#55)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| GPQA Diamond | 65.7% | 87% |
| Confabulations | 18.4% | 12.4% |
| MMLU-Pro | — | 85.1% |
| GPQA (HELM) | — | 72.7% |
| LMArena Expert | — | 1415 |
Multimodal Not comparable
Gemini 2.0 Pro: —, Grok 4: 33.7 (#94)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 45% |
Multilingual Not comparable
Gemini 2.0 Pro: —, Grok 4: 51.8 (#103)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| LMArena Non-English | — | 1403 |
| LMArena Chinese | — | 1427 |
| LMArena French | — | 1418 |
| LMArena German | — | 1429 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1377 |
| LMArena Russian | — | 1410 |
| LMArena Spanish | — | 1420 |
Instruction Following Grok 4 leads
Gemini 2.0 Pro: 75.5 (#59), Grok 4: 79.2 (#5)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| LiveBench Instruction Following | 83.4% | — |
| IFEval | — | 94.9% |
| LMArena Instruction Following | — | 1387 |
Long Context Grok 4 leads
Gemini 2.0 Pro: 29.2 (#292), Grok 4: 63.1 (#4)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| Fiction.LiveBench | 41.7% | 94.4% |
| LMArena Longer Query | — | 1409 |
Writing & Preference Grok 4 leads
Gemini 2.0 Pro: 52.7 (#165), Grok 4: 58.5 (#116)
| Benchmark | Gemini 2.0 Pro | Grok 4 |
|---|---|---|
| LMArena Text | — | 1411 |
| LMArena Creative Writing | — | 1397 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |
| LMArena Multi-Turn | — | 1416 |
| LiveBench Language | 44.9% | — |
Frequently asked questions
Is Gemini 2.0 Pro better than Grok 4?
Grok 4 is the stronger model overall, scoring 48.1 to 39.1 on the Noometry Index.
Is Gemini 2.0 Pro or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 37.8 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Pro and Grok 4 share?
5 benchmarks have published results for both models. Gemini 2.0 Pro has 14 scored results on Noometry and Grok 4 has 48.