Model comparison
Gemini 2.0 Flash (Feb 2025) vs Grok 4
Grok 4 is the stronger model overall, scoring 48.1 to 35.1 on the Noometry Index.
Last verified . 36 shared benchmarks.
GoogleSummary
- They share 36 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and Grok 4 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 38.1.
- The biggest single-benchmark swing is Aider Polyglot: 38.2% for Gemini 2.0 Flash (Feb 2025) and 79.6% for Grok 4.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Grok 4 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 35.1 | 48.1 |
| Released | 2024-12-06 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Grok 4: 50.3 (#46)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| Aider Polyglot | 38.2% | 79.6% |
| WeirdML | 25.8% | 45.7% |
| LMArena Coding | 1350 | 1408 |
| SWE-bench Verified (bash only) | 13.5% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Grok 4: 32.3 (#68)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| TheAgentCompany | 11.4% | — |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Grok 4: 36.7 (#65)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 16% |
| SimpleBench | 31.1% | 60.5% |
| Kagi LLM Benchmark | 37.8% | 73.6% |
| LMArena Hard Prompts | 1346 | 1409 |
| Epoch Capabilities Index | 135.36 | 146.44 |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| ForecastBench | — | 60.9 |
| LiveBench | 66.9% | — |
Math Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Grok 4: 48.4 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 84% |
| Omni-MATH | 45.9% | 60.3% |
| LMArena Math | 1352 | 1422 |
| FrontierMath (Feb 2025 set) | 1.7% | 19.7% |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Grok 4: 53.8 (#55)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| GPQA Diamond | 64.1% | 87% |
| MMLU-Pro | 73.7% | 85.1% |
| Confabulations | 12.4% | 12.4% |
| GPQA (HELM) | 55.6% | 72.7% |
| LMArena Expert | 1339 | 1415 |
| Humanity's Last Exam | 6.6% | — |
| MMLU | 79.7% | — |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Grok 4: 33.7 (#94)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| LMArena Vision | 1158 | 1210 |
| GeoBench | 77% | 45% |
Multilingual Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Grok 4: 51.8 (#103)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| LMArena Non-English | 1342 | 1403 |
| LMArena Chinese | 1373 | 1427 |
| LMArena French | 1391 | 1418 |
| LMArena German | 1353 | 1429 |
| LMArena Japanese | 1294 | 1394 |
| LMArena Korean | 1313 | 1377 |
| LMArena Russian | 1351 | 1410 |
| LMArena Spanish | 1363 | 1420 |
Instruction Following Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Grok 4: 79.2 (#5)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| IFEval | 84.1% | 94.9% |
| LMArena Instruction Following | 1336 | 1387 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Grok 4: 63.1 (#4)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 94.4% |
| LMArena Longer Query | 1344 | 1409 |
Writing & Preference Grok 4 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Grok 4: 58.5 (#116)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok 4 |
|---|---|---|
| LMArena Text | 1354 | 1411 |
| LMArena Creative Writing | 1340 | 1397 |
| Short-Story Creative Writing | 73.8% | 76.9% |
| WildBench | 80% | 79.7% |
| LMArena Multi-Turn | 1350 | 1416 |
| EQ-Bench Creative Writing | 1128 | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Grok 4?
Grok 4 is the stronger model overall, scoring 48.1 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Grok 4 share?
36 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Grok 4 has 48.