Model comparison
Gemini 2.0 Flash (Feb 2025) vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 35.1 on the Noometry Index.
Last verified . 34 shared benchmarks.
GoogleSummary
- They share 34 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and Grok-3 mini in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 32.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Gemini 2.0 Flash (Feb 2025) and 61.3% for Grok-3 mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Grok-3 mini | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 35.1 | 41.2 |
| Released | 2024-12-06 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Grok-3 mini: 40.8 (#131)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| Aider Polyglot | 38.2% | 49.3% |
| WeirdML | 25.8% | 42.6% |
| LMArena Coding | 1350 | 1379 |
| SWE-bench Verified (bash only) | 13.5% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Grok-3 mini: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Grok-3 mini: 13.6 (#334)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0.4% |
| Kagi LLM Benchmark | 37.8% | 61.3% |
| LMArena Hard Prompts | 1346 | 1375 |
| Epoch Capabilities Index | 135.36 | 140.35 |
| SimpleBench | 31.1% | — |
| ARC-AGI-1 | — | 16.5% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LiveBench | 66.9% | — |
Math Grok-3 mini leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Grok-3 mini: 42.1 (#85)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 77.8% |
| Omni-MATH | 45.9% | 31.8% |
| LMArena Math | 1352 | 1386 |
| MATH Level 5 | 82.2% | 90.9% |
| FrontierMath (Feb 2025 set) | 1.7% | 5.9% |
| LiveBench Math | 75.8% | — |
Knowledge Grok-3 mini leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Grok-3 mini: 46.4 (#81)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 64.1% | 76.3% |
| MMLU-Pro | 73.7% | 79.9% |
| Confabulations | 12.4% | 10.8% |
| GPQA (HELM) | 55.6% | 67.5% |
| LMArena Expert | 1339 | 1395 |
| Humanity's Last Exam | 6.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Grok-3 mini: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Too close to call
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Grok-3 mini: 48.1 (#145)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1342 | 1352 |
| LMArena Chinese | 1373 | 1387 |
| LMArena French | 1391 | 1357 |
| LMArena German | 1353 | 1349 |
| LMArena Japanese | 1294 | 1342 |
| LMArena Korean | 1313 | 1335 |
| LMArena Russian | 1351 | 1353 |
| LMArena Spanish | 1363 | 1381 |
Instruction Following Grok-3 mini leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Grok-3 mini: 78.5 (#9)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| IFEval | 84.1% | 95.1% |
| LMArena Instruction Following | 1336 | 1357 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Grok-3 mini leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Grok-3 mini: 41.0 (#147)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 61.1% | 66.7% |
| LMArena Longer Query | 1344 | 1372 |
Writing & Preference Grok-3 mini leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Grok-3 mini: 52.5 (#169)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-3 mini |
|---|---|---|
| LMArena Text | 1354 | 1370 |
| LMArena Creative Writing | 1340 | 1342 |
| Short-Story Creative Writing | 73.8% | 73.5% |
| WildBench | 80% | 65.1% |
| LMArena Multi-Turn | 1350 | 1355 |
| EQ-Bench Creative Writing | 1128 | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Grok-3 mini share?
34 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Grok-3 mini has 35.