Model comparison
Gemini 3.5 Flash vs Grok-3 mini
Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 41.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.7 to 13.8.
- The biggest single-benchmark swing is ARC-AGI-1: 92.5% for Gemini 3.5 Flash and 16.5% for Grok-3 mini.
Side by side
| Gemini 3.5 Flash | Grok-3 mini | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 54.1 | 41.0 |
| Released | 2026-05-19 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $9 | — |
| Results tracked | 54 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash leads
Gemini 3.5 Flash: 49.1 (#46), Grok-3 mini: 40.4 (#126)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| WeirdML | 62.6% | 42.6% |
| LMArena Coding | 1492 | 1380 |
| SWE-bench Verified | 79.3% | — |
| DeepSWE | 37.4% | — |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1499 | — |
| SciCode | 53.1% | — |
| ALE-Bench | 911.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.5 Flash: 24.8 (#107), Grok-3 mini: —
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| APEX-Agents | 27.5% | — |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | 5,396 | — |
Reasoning Gemini 3.5 Flash leads
Gemini 3.5 Flash: 62.7 (#16), Grok-3 mini: 13.8 (#323)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 72.1% | 0.4% |
| ARC-AGI-1 | 92.5% | 16.5% |
| LMArena Hard Prompts | 1488 | 1374 |
| Epoch Capabilities Index | 154.55 | 140.35 |
| SimpleBench | 76.7% | — |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 92.6% | — |
| CritPt | 13.1% | — |
| Chess Puzzles | 50% | — |
| EnigmaEval | 25.4% | — |
| EBR-Bench | 4.8% | — |
| Mystery Game Puzzles | 32% | — |
| DTBench | 94.7% | — |
| LMCA | 47.1% | — |
| Surface Evolver Bench | 58.1% | — |
| ForecastBench | 59 | — |
Math Gemini 3.5 Flash leads
Gemini 3.5 Flash: 60.5 (#30), Grok-3 mini: 40.3 (#78)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 77.8% |
| LMArena Math | 1502 | 1386 |
| FrontierMath (Feb 2025 set) | 39% | 5.9% |
| FrontierMath (Tiers 1-3) | 62.8% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| ProofBench | 31% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Gemini 3.5 Flash leads
Gemini 3.5 Flash: 66.3 (#10), Grok-3 mini: 46.3 (#75)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 92.8% | 76.3% |
| LMArena Expert | 1493 | 1395 |
| SimpleQA Verified | 66.2% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
Gemini 3.5 Flash: 45.7 (#13), Grok-3 mini: —
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1311 | — |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |
Multilingual Gemini 3.5 Flash leads
Gemini 3.5 Flash: 57.1 (#12), Grok-3 mini: 48.3 (#141)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1475 | 1352 |
| LMArena Chinese | 1525 | 1387 |
| LMArena French | 1490 | 1357 |
| LMArena German | 1500 | 1350 |
| LMArena Japanese | 1481 | 1343 |
| LMArena Korean | 1453 | 1336 |
| LMArena Russian | 1491 | 1352 |
| LMArena Spanish | 1478 | 1379 |
Instruction Following Grok-3 mini leads
Gemini 3.5 Flash: 77.2 (#29), Grok-3 mini: 78.7 (#8)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1466 | 1356 |
| IFEval | — | 95.1% |
Long Context Gemini 3.5 Flash leads
Gemini 3.5 Flash: 45.3 (#39), Grok-3 mini: 41.0 (#142)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1481 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Gemini 3.5 Flash leads
Gemini 3.5 Flash: 65.5 (#46), Grok-3 mini: 52.7 (#163)
| Benchmark | Gemini 3.5 Flash | Grok-3 mini |
|---|---|---|
| LMArena Text | 1481 | 1370 |
| LMArena Creative Writing | 1467 | 1342 |
| LMArena Multi-Turn | 1482 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
| EQ-Bench 4 | 1087 | — |
Frequently asked questions
Is Gemini 3.5 Flash better than Grok-3 mini?
Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 41.0 on the Noometry Index.
Is Gemini 3.5 Flash or Grok-3 mini better for coding?
Gemini 3.5 Flash scores higher on coding benchmarks: 49.1 versus 40.4 in the Noometry coding category.
How many benchmarks do Gemini 3.5 Flash and Grok-3 mini share?
24 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Grok-3 mini has 35.