Model comparison
Gemini 3.6 Flash vs Grok 4
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 48.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 7 categories and Grok 4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 36.7.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Gemini 3.6 Flash and 16% for Grok 4.
Side by side
| Gemini 3.6 Flash | Grok 4 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 54.1 | 48.1 |
| Released | 2026-07-21 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $3.75 | — |
| Results tracked | 46 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.6 Flash: 50.0 (#48), Grok 4: 50.3 (#46)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| WeirdML | 56.1% | 45.7% |
| LMArena Coding | 1491 | 1408 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1538 | — |
| SciCode | 52.7% | — |
| ALE-Bench | 715.52 | — |
Agentic & Tool Use Too close to call
Gemini 3.6 Flash: 32.3 (#65), Grok 4: 32.3 (#68)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| APEX-Agents | 46.9% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Gemini 3.6 Flash leads
Gemini 3.6 Flash: 58.8 (#22), Grok 4: 36.7 (#65)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 16% |
| ARC-AGI-1 | 91.2% | 66.7% |
| Chess Puzzles | 43% | 28% |
| LMArena Hard Prompts | 1485 | 1409 |
| Epoch Capabilities Index | 154.25 | 146.44 |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| NYT Connections (extended) | 89% | — |
| CritPt | 10.6% | — |
| Mystery Game Puzzles | 30% | — |
| DTBench | 95.5% | — |
| LMCA | 44.9% | — |
| ForecastBench | — | 60.9 |
Math Gemini 3.6 Flash leads
Gemini 3.6 Flash: 57.3 (#40), Grok 4: 48.4 (#64)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.2% | 84% |
| LMArena Math | 1505 | 1422 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| ProofBench | 36% | — |
| Omni-MATH | — | 60.3% |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#8), Grok 4: 53.8 (#55)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| GPQA Diamond | 94.1% | 87% |
| LMArena Expert | 1488 | 1415 |
| SimpleQA Verified | 66.2% | — |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
Multimodal Gemini 3.6 Flash leads
Gemini 3.6 Flash: 38.5 (#64), Grok 4: 33.7 (#94)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| LMArena Vision | 1298 | 1210 |
| GeoBench | — | 45% |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.5 (#19), Grok 4: 51.8 (#103)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| LMArena Non-English | 1469 | 1403 |
| LMArena Chinese | 1531 | 1427 |
| LMArena French | 1504 | 1418 |
| LMArena German | 1478 | 1429 |
| LMArena Japanese | 1476 | 1394 |
| LMArena Korean | 1431 | 1377 |
| LMArena Russian | 1487 | 1410 |
| LMArena Spanish | 1475 | 1420 |
Instruction Following Grok 4 leads
Gemini 3.6 Flash: 77.0 (#33), Grok 4: 79.2 (#5)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
Gemini 3.6 Flash: 45.1 (#50), Grok 4: 63.1 (#4)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1474 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Gemini 3.6 Flash leads
Gemini 3.6 Flash: 68.2 (#27), Grok 4: 58.5 (#116)
| Benchmark | Gemini 3.6 Flash | Grok 4 |
|---|---|---|
| LMArena Text | 1479 | 1411 |
| LMArena Creative Writing | 1465 | 1397 |
| LMArena Multi-Turn | 1481 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 1604 | — |
| WildBench | — | 79.7% |
Frequently asked questions
Is Gemini 3.6 Flash better than Grok 4?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 48.1 on the Noometry Index.
Is Gemini 3.6 Flash or Grok 4 better for coding?
They score almost the same on coding (50.0 vs 50.3); test both on your own repository before choosing.
How many benchmarks do Gemini 3.6 Flash and Grok 4 share?
25 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Grok 4 has 48.