Model comparison
Gemini 2.0 Flash (Feb 2025) vs Grok-2 (Dec 2024)
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 33.7 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 5 categories and Grok-2 (Dec 2024) in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 11.5% for Grok-2 (Dec 2024).
Side by side
| Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 35.1 | 33.7 |
| Released | 2024-12-06 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 25.8% | 22.2% |
| LiveBench Coding | 63.4% | 46.4% |
| LMArena Coding | 1350 | 1287 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| BigCodeBench Instruct | 45.9% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Grok-2 (Dec 2024): —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Grok-2 (Dec 2024) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 31.1% | 22.7% |
| LiveBench Reasoning | 78.2% | 54.8% |
| LMArena Hard Prompts | 1346 | 1272 |
| DTBench | 63.2% | 65.2% |
| LiveBench Data Analysis | 69.4% | 54.5% |
| Epoch Capabilities Index | 135.36 | 130.48 |
| LiveBench | 66.9% | 54.3% |
| ARC-AGI-2 | 1.3% | — |
| Kagi LLM Benchmark | 37.8% | — |
| EnigmaEval | 1.1% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 11.5% |
| LiveBench Math | 75.8% | 54.9% |
| LMArena Math | 1352 | 1283 |
| MATH Level 5 | 82.2% | 63.5% |
| FrontierMath (Feb 2025 set) | 1.7% | 0.7% |
| Omni-MATH | 45.9% | — |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 64.1% | 53.8% |
| Confabulations | 12.4% | 20.1% |
| LMArena Expert | 1339 | 1254 |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Grok-2 (Dec 2024): —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1342 | 1282 |
| LMArena Chinese | 1373 | 1289 |
| LMArena French | 1391 | 1318 |
| LMArena German | 1353 | 1287 |
| LMArena Japanese | 1294 | 1244 |
| LMArena Korean | 1313 | 1237 |
| LMArena Russian | 1351 | 1286 |
| LMArena Spanish | 1363 | 1281 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 69.6% |
| LMArena Instruction Following | 1336 | 1270 |
| IFEval | 84.1% | — |
Long Context Too close to call
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1344 | 1276 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Too close to call
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1354 | 1305 |
| LMArena Creative Writing | 1340 | 1284 |
| Short-Story Creative Writing | 73.8% | 63.6% |
| LMArena Multi-Turn | 1350 | 1290 |
| LiveBench Language | 51.3% | 45.6% |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Grok-2 (Dec 2024)?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 33.7 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Grok-2 (Dec 2024) better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Grok-2 (Dec 2024) share?
34 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Grok-2 (Dec 2024) has 34.