Model comparison
Gemini 3 Flash Preview vs Grok 4
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 48.1 on the Noometry Index.
Last verified . 34 shared benchmarks.
GoogleSummary
- They share 34 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and Grok 4 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 44.4.
- The biggest single-benchmark swing is GeoBench: 88% for Gemini 3 Flash Preview and 45% for Grok 4.
Side by side
| Gemini 3 Flash Preview | Grok 4 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 52.3 | 48.1 |
| Released | 2025-12-17 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $3 | — |
| Results tracked | 59 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3 Flash Preview: 50.9 (#42), Grok 4: 50.3 (#46)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| WeirdML | 61.6% | 45.7% |
| LMArena Coding | 1460 | 1408 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| ALE-Bench | 1,367 | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), Grok 4: 32.3 (#68)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| Terminal-Bench | 64.3% | 27.2% |
| DeepResearch Bench | 49.8% | 47.3% |
| BALROG | 48.1% | 43.6% |
| LMArena Search | 1198 | 1142 |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| Cybench | — | 43% |
| GDP.pdf | 10% | — |
| METR Time Horizons | — | 66.6% |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Grok 4: 36.7 (#65)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 33.6% | 16% |
| SimpleBench | 61.1% | 60.5% |
| ARC-AGI-1 | 84.7% | 66.7% |
| Chess Puzzles | 40% | 28% |
| LMArena Hard Prompts | 1465 | 1409 |
| Epoch Capabilities Index | 151.8 | 146.44 |
| ForecastBench | 58.5 | 60.9 |
| Kagi LLM Benchmark | — | 73.6% |
| NYT Connections (extended) | 83.1% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 89.1% | — |
| LMCA | 43.1% | — |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), Grok 4: 48.4 (#64)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 84% |
| LMArena Math | 1473 | 1422 |
| FrontierMath (Feb 2025 set) | 35.6% | 19.7% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| Omni-MATH | — | 60.3% |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Grok 4: 53.8 (#55)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| GPQA Diamond | 89.4% | 87% |
| LMArena Expert | 1462 | 1415 |
| SimpleQA Verified | 66.8% | — |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 13.5% | — |
| GPQA (HELM) | — | 72.7% |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), Grok 4: 33.7 (#94)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| LMArena Vision | 1285 | 1210 |
| GeoBench | 88% | 45% |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Grok 4: 51.8 (#103)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| LMArena Non-English | 1458 | 1403 |
| LMArena Chinese | 1511 | 1427 |
| LMArena French | 1477 | 1418 |
| LMArena German | 1497 | 1429 |
| LMArena Japanese | 1489 | 1394 |
| LMArena Korean | 1443 | 1377 |
| LMArena Russian | 1480 | 1410 |
| LMArena Spanish | 1469 | 1420 |
Instruction Following Grok 4 leads
Gemini 3 Flash Preview: 75.7 (#56), Grok 4: 79.2 (#5)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
Gemini 3 Flash Preview: 44.4 (#67), Grok 4: 63.1 (#4)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1452 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), Grok 4: 58.5 (#116)
| Benchmark | Gemini 3 Flash Preview | Grok 4 |
|---|---|---|
| LMArena Text | 1466 | 1411 |
| LMArena Creative Writing | 1457 | 1397 |
| LMArena Multi-Turn | 1471 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |
Frequently asked questions
Is Gemini 3 Flash Preview better than Grok 4?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 48.1 on the Noometry Index.
Is Gemini 3 Flash Preview or Grok 4 better for coding?
They score almost the same on coding (50.9 vs 50.3); test both on your own repository before choosing.
How many benchmarks do Gemini 3 Flash Preview and Grok 4 share?
34 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Grok 4 has 48.