Model comparison
Gemini 3.8 Flash vs Grok 4.3
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 43.8 on the Noometry Index.
Last verified . 37 shared benchmarks.
GoogleSummary
- They share 37 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 10 categories and Grok 4.3 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 35.9.
- The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.8 Flash and 55.2% for Grok 4.3.
- Both cost about the same: $0.75 input and $3.75 output per million tokens.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Gemini 3.8 Flash | Grok 4.3 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 61.8 | 43.8 |
| Released | 2026-09-02 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 66K | 30K |
| Input $ / M tokens | $0.75 | $1.25 |
| Output $ / M tokens | $3.75 | $2.50 |
| Results tracked | 50 | 40 |
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 4.3: 41.6 (#121)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1584 | 1357 |
| SciCode | 56.6% | 47.3% |
| WeirdML | 84.8% | 49.9% |
| LMArena Coding | 1510 | 1415 |
| ALE-Bench | 1,270 | 944.17 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.8 Flash: 41.8 (#21), Grok 4.3: 27.7 (#99)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| GDP.pdf | 23.4% | 8% |
| Vending-Bench 2 | 5,094 | 35.26 |
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| LMArena Search | — | 1165 |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), Grok 4.3: 35.9 (#68)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 97.4% | 55.2% |
| CritPt | 18.3% | 8% |
| Chess Puzzles | 61% | 25% |
| LMArena Hard Prompts | 1508 | 1396 |
| DTBench | 95.7% | 90.7% |
| LMCA | 52.9% | 38.3% |
| Epoch Capabilities Index | 156.71 | 149.16 |
| ARC-AGI-2 | 89.2% | — |
| ARC-AGI-1 | 98.5% | — |
| Mystery Game Puzzles | 47% | — |
| Surface Evolver Bench | 76.9% | — |
| ForecastBench | — | 60.3 |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), Grok 4.3: 46.0 (#74)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 42.8% |
| FrontierMath Tier 4 | 22% | 14.6% |
| OTIS Mock AIME 2024-2025 | 98.9% | 93.3% |
| ProofBench | 48% | 11% |
| LMArena Math | 1528 | 1388 |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), Grok 4.3: 52.5 (#62)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 95.4% | 88.8% |
| SimpleQA Verified | 69.7% | 33.2% |
| LMArena Expert | 1524 | 1385 |
| Humanity's Last Exam | 44.5% | — |
Multimodal Gemini 3.8 Flash leads
Gemini 3.8 Flash: 40.7 (#45), Grok 4.3: 31.6 (#104)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1314 | 1229 |
| Blueprint-Bench 2 | 38.6% | 0% |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), Grok 4.3: 50.5 (#120)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1491 | 1385 |
| LMArena Chinese | 1554 | 1422 |
| LMArena French | 1498 | 1412 |
| LMArena German | 1493 | 1395 |
| LMArena Japanese | 1502 | 1379 |
| LMArena Korean | 1459 | 1356 |
| LMArena Russian | 1515 | 1399 |
| LMArena Spanish | 1485 | 1398 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), Grok 4.3: 72.1 (#140)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1490 | 1366 |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), Grok 4.3: 42.5 (#123)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1508 | 1393 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), Grok 4.3: 58.5 (#118)
| Benchmark | Gemini 3.8 Flash | Grok 4.3 |
|---|---|---|
| LMArena Text | 1499 | 1397 |
| LMArena Creative Writing | 1492 | 1380 |
| LMArena Multi-Turn | 1501 | 1406 |
| EQ-Bench Creative Writing | 1748 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is Gemini 3.8 Flash better than Grok 4.3?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 43.8 on the Noometry Index.
Which is cheaper, Gemini 3.8 Flash or Grok 4.3?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is Gemini 3.8 Flash or Grok 4.3 better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Gemini 3.8 Flash and Grok 4.3 share?
37 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Grok 4.3 has 40.