Model comparison
Gemini 3 Flash Preview vs Grok-2 (Dec 2024)
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 16.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 11.5% for Grok-2 (Dec 2024).
Side by side
| Gemini 3 Flash Preview | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 52.3 | 33.7 |
| Released | 2025-12-17 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $3 | — |
| Results tracked | 59 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 61.6% | 22.2% |
| LMArena Coding | 1460 | 1287 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 1,367 | — |
Agentic & Tool Use Not comparable
Gemini 3 Flash Preview: 38.7 (#29), Grok-2 (Dec 2024): —
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 61.1% | 22.7% |
| LMArena Hard Prompts | 1465 | 1272 |
| DTBench | 89.1% | 65.2% |
| Epoch Capabilities Index | 151.8 | 130.48 |
| ARC-AGI-2 | 33.6% | — |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| Chess Puzzles | 40% | — |
| LiveBench Reasoning | — | 54.8% |
| Mystery Game Puzzles | 26% | — |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 43.1% | — |
| ForecastBench | 58.5 | — |
| LiveBench | — | 54.3% |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 11.5% |
| LMArena Math | 1473 | 1283 |
| FrontierMath (Feb 2025 set) | 35.6% | 0.7% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 89.4% | 53.8% |
| LMArena Expert | 1462 | 1254 |
| SimpleQA Verified | 66.8% | — |
| Confabulations | — | 20.1% |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), Grok-2 (Dec 2024): —
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1458 | 1282 |
| LMArena Chinese | 1511 | 1289 |
| LMArena French | 1477 | 1318 |
| LMArena German | 1497 | 1287 |
| LMArena Japanese | 1489 | 1244 |
| LMArena Korean | 1443 | 1237 |
| LMArena Russian | 1480 | 1286 |
| LMArena Spanish | 1469 | 1281 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 75.7 (#56), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1437 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 44.4 (#67), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1452 | 1276 |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Gemini 3 Flash Preview | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1466 | 1305 |
| LMArena Creative Writing | 1457 | 1284 |
| LMArena Multi-Turn | 1471 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Gemini 3 Flash Preview better than Grok-2 (Dec 2024)?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.7 on the Noometry Index.
Is Gemini 3 Flash Preview or Grok-2 (Dec 2024) better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 33.3 in the Noometry coding category.
How many benchmarks do Gemini 3 Flash Preview and Grok-2 (Dec 2024) share?
24 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Grok-2 (Dec 2024) has 34.