Model comparison
Gemini 3.8 Flash vs Grok-3 mini
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 41.2 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 7 categories and Grok-3 mini in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Gemini 3.8 Flash and 0.4% for Grok-3 mini.
Side by side
| Gemini 3.8 Flash | Grok-3 mini | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 61.8 | 41.2 |
| Released | 2026-09-02 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $3.75 | — |
| Results tracked | 50 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 59.2 (#15), Grok-3 mini: 40.8 (#131)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| WeirdML | 84.8% | 42.6% |
| LMArena Coding | 1510 | 1379 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| Aider Polyglot | — | 49.3% |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1584 | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Not comparable
Gemini 3.8 Flash: 41.8 (#21), Grok-3 mini: —
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), Grok-3 mini: 13.6 (#334)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 89.2% | 0.4% |
| ARC-AGI-1 | 98.5% | 16.5% |
| LMArena Hard Prompts | 1508 | 1375 |
| Epoch Capabilities Index | 156.71 | 140.35 |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 97.4% | — |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), Grok-3 mini: 42.1 (#85)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 77.8% |
| LMArena Math | 1528 | 1386 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), Grok-3 mini: 46.4 (#81)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 95.4% | 76.3% |
| LMArena Expert | 1524 | 1395 |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
Gemini 3.8 Flash: 40.7 (#45), Grok-3 mini: —
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), Grok-3 mini: 48.1 (#145)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1491 | 1352 |
| LMArena Chinese | 1554 | 1387 |
| LMArena French | 1498 | 1357 |
| LMArena German | 1493 | 1349 |
| LMArena Japanese | 1502 | 1342 |
| LMArena Korean | 1459 | 1335 |
| LMArena Russian | 1515 | 1353 |
| LMArena Spanish | 1485 | 1381 |
Instruction Following Too close to call
Gemini 3.8 Flash: 78.0 (#13), Grok-3 mini: 78.5 (#9)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1490 | 1357 |
| IFEval | — | 95.1% |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), Grok-3 mini: 41.0 (#147)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1508 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), Grok-3 mini: 52.5 (#169)
| Benchmark | Gemini 3.8 Flash | Grok-3 mini |
|---|---|---|
| LMArena Text | 1499 | 1370 |
| LMArena Creative Writing | 1492 | 1342 |
| LMArena Multi-Turn | 1501 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1748 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is Gemini 3.8 Flash better than Grok-3 mini?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 41.2 on the Noometry Index.
Is Gemini 3.8 Flash or Grok-3 mini better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 40.8 in the Noometry coding category.
How many benchmarks do Gemini 3.8 Flash and Grok-3 mini share?
23 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Grok-3 mini has 35.