Model comparison
Gemini 3.1 Flash Lite vs Grok-3 mini
Gemini 3.1 Flash Lite and Grok-3 mini score almost the same on the Noometry Index (40.8 vs 41.2), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 4 categories and Grok-3 mini in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Flash Lite leads 22.9 to 13.6.
- The biggest single-benchmark swing is WeirdML: 52.2% for Gemini 3.1 Flash Lite and 42.6% for Grok-3 mini.
Side by side
| Gemini 3.1 Flash Lite | Grok-3 mini | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 40.8 | 41.2 |
| Released | 2026-03-03 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 38 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Gemini 3.1 Flash Lite: 37.8 (#188), Grok-3 mini: 40.8 (#131)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| WeirdML | 52.2% | 42.6% |
| LMArena Coding | 1400 | 1379 |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 30.2 (#79), Grok-3 mini: —
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
Reasoning Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 22.9 (#186), Grok-3 mini: 13.6 (#334)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 61.3% |
| LMArena Hard Prompts | 1407 | 1375 |
| Epoch Capabilities Index | 144.47 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| NYT Connections (extended) | 8.2% | — |
| ARC-AGI-1 | — | 16.5% |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| ForecastBench | 54.4 | — |
Math Grok-3 mini leads
Gemini 3.1 Flash Lite: 40.7 (#90), Grok-3 mini: 42.1 (#85)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 77.8% |
| LMArena Math | 1428 | 1386 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Gemini 3.1 Flash Lite: 41.9 (#104), Grok-3 mini: 46.4 (#81)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 81.8% | 76.3% |
| LMArena Expert | 1398 | 1395 |
| Humanity's Last Exam | 8.6% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), Grok-3 mini: —
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), Grok-3 mini: 48.1 (#145)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1411 | 1352 |
| LMArena Chinese | 1461 | 1387 |
| LMArena French | 1424 | 1357 |
| LMArena German | 1429 | 1349 |
| LMArena Japanese | 1413 | 1342 |
| LMArena Korean | 1392 | 1335 |
| LMArena Russian | 1420 | 1353 |
| LMArena Spanish | 1421 | 1381 |
Instruction Following Grok-3 mini leads
Gemini 3.1 Flash Lite: 72.7 (#131), Grok-3 mini: 78.5 (#9)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1377 | 1357 |
| IFEval | — | 95.1% |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#122), Grok-3 mini: 41.0 (#147)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1394 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 60.9 (#94), Grok-3 mini: 52.5 (#169)
| Benchmark | Gemini 3.1 Flash Lite | Grok-3 mini |
|---|---|---|
| LMArena Text | 1416 | 1370 |
| LMArena Creative Writing | 1401 | 1342 |
| LMArena Multi-Turn | 1417 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Grok-3 mini?
Gemini 3.1 Flash Lite and Grok-3 mini score almost the same on the Noometry Index (40.8 vs 41.2), so choose on price, context window or the category you care about most.
Is Gemini 3.1 Flash Lite or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 37.8 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Flash Lite and Grok-3 mini share?
22 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Grok-3 mini has 35.