Model comparison
Gemini 3.5 Flash Lite vs Grok 3
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 39.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 6 categories and Grok 3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash Lite leads 27.8 to 13.7.
- The biggest single-benchmark swing is ARC-AGI-1: 53.5% for Gemini 3.5 Flash Lite and 5.5% for Grok 3.
Side by side
| Gemini 3.5 Flash Lite | Grok 3 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 41.5 | 39.9 |
| Released | 2026-07-21 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 39 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.5 Flash Lite: 42.4 (#104), Grok 3: 41.9 (#115)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| WeirdML | 39% | 37.2% |
| LMArena Coding | 1453 | 1432 |
| Aider Polyglot | — | 53.3% |
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use Grok 3 leads
Gemini 3.5 Flash Lite: 25.7 (#107), Grok 3: 30.5 (#76)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| APEX-Agents | 29.3% | — |
| BALROG | — | 29.5% |
| GDP.pdf | 10% | — |
Reasoning Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 27.8 (#114), Grok 3: 13.7 (#333)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 10.3% | 0% |
| ARC-AGI-1 | 53.5% | 5.5% |
| LMArena Hard Prompts | 1441 | 1434 |
| Epoch Capabilities Index | 145.13 | 138.33 |
| SimpleBench | — | 36.1% |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 60.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 22% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
Math Grok 3 leads
Gemini 3.5 Flash Lite: 25.9 (#264), Grok 3: 38.0 (#145)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 55.6% |
| LMArena Math | 1433 | 1391 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| ProofBench | 13% | — |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 50.1 (#72), Grok 3: 46.2 (#82)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| GPQA Diamond | 83.3% | 75.8% |
| LMArena Expert | 1435 | 1421 |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
Gemini 3.5 Flash Lite: 41.1 (#40), Grok 3: —
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| LMArena Vision | 1268 | — |
Multilingual Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 53.5 (#63), Grok 3: 52.3 (#87)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| LMArena Non-English | 1427 | 1410 |
| LMArena Chinese | 1469 | 1448 |
| LMArena French | 1451 | 1460 |
| LMArena German | 1454 | 1431 |
| LMArena Japanese | 1427 | 1387 |
| LMArena Korean | 1407 | 1373 |
| LMArena Russian | 1443 | 1416 |
| LMArena Spanish | 1442 | 1417 |
Instruction Following Too close to call
Gemini 3.5 Flash Lite: 74.8 (#85), Grok 3: 75.0 (#73)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1409 |
| IFEval | — | 88.4% |
Long Context Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 43.9 (#84), Grok 3: 38.7 (#192)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1435 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.2 (#57), Grok 3: 55.8 (#141)
| Benchmark | Gemini 3.5 Flash Lite | Grok 3 |
|---|---|---|
| LMArena Text | 1435 | 1426 |
| LMArena Creative Writing | 1420 | 1414 |
| EQ-Bench Creative Writing | 1559 | 1186 |
| LMArena Multi-Turn | 1445 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
| WildBench | — | 84.9% |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than Grok 3?
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 39.9 on the Noometry Index.
Is Gemini 3.5 Flash Lite or Grok 3 better for coding?
They score almost the same on coding (42.4 vs 41.9); test both on your own repository before choosing.
How many benchmarks do Gemini 3.5 Flash Lite and Grok 3 share?
24 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Grok 3 has 40.