Model comparison
Gemini 3.8 Flash vs GPT-4.1
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 35.9 on the Noometry Index.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 10 categories and GPT-4.1 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 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 98.5% for Gemini 3.8 Flash and 5.5% for GPT-4.1.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $8 for GPT-4.1.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 3.8 Flash | GPT-4.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 61.8 | 35.9 |
| Released | 2026-09-02 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $3.75 | $8 |
| Results tracked | 50 | 52 |
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), GPT-4.1: 34.4 (#238)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| WeirdML | 84.8% | 39% |
| LMArena Coding | 1510 | 1391 |
| ALE-Bench | 1,270 | 558.1 |
| SWE-bench Verified | — | 48.5% |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1584 | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| CadEval | — | 42% |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.8 Flash: 41.8 (#21), GPT-4.1: 34.7 (#43)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 54% |
| 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), GPT-4.1: 11.7 (#339)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 89.2% | 0.4% |
| ARC-AGI-1 | 98.5% | 5.5% |
| Chess Puzzles | 61% | 6% |
| LMArena Hard Prompts | 1508 | 1384 |
| DTBench | 95.7% | 68.3% |
| LMCA | 52.9% | 25.6% |
| Epoch Capabilities Index | 156.71 | 136.78 |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| NYT Connections (extended) | 97.4% | — |
| CritPt | 18.3% | — |
| EnigmaEval | — | 2.2% |
| Mystery Game Puzzles | 47% | — |
| Surface Evolver Bench | 76.9% | — |
| ForecastBench | — | 61.5 |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), GPT-4.1: 22.3 (#280)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 6% |
| OTIS Mock AIME 2024-2025 | 98.9% | 38.3% |
| LMArena Math | 1528 | 1370 |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), GPT-4.1: 37.1 (#160)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 95.4% | 66.9% |
| Humanity's Last Exam | 44.5% | 5.4% |
| SimpleQA Verified | 69.7% | 31.1% |
| LMArena Expert | 1524 | 1364 |
| MMLU-Pro | — | 81.1% |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |
Multimodal Gemini 3.8 Flash leads
Gemini 3.8 Flash: 40.7 (#45), GPT-4.1: 38.2 (#67)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1314 | 1211 |
| GeoBench | — | 72% |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), GPT-4.1: 49.4 (#133)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1491 | 1370 |
| LMArena Chinese | 1554 | 1382 |
| LMArena French | 1498 | 1382 |
| LMArena German | 1493 | 1381 |
| LMArena Japanese | 1502 | 1319 |
| LMArena Korean | 1459 | 1339 |
| LMArena Russian | 1515 | 1377 |
| LMArena Spanish | 1485 | 1376 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), GPT-4.1: 71.3 (#153)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1490 | 1367 |
| IFEval | — | 83.8% |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), GPT-4.1: 40.0 (#163)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1508 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), GPT-4.1: 57.6 (#125)
| Benchmark | Gemini 3.8 Flash | GPT-4.1 |
|---|---|---|
| LMArena Text | 1499 | 1383 |
| LMArena Creative Writing | 1492 | 1363 |
| EQ-Bench Creative Writing | 1748 | 1420 |
| LMArena Multi-Turn | 1501 | 1398 |
| WildBench | — | 85.4% |
Frequently asked questions
Is Gemini 3.8 Flash better than GPT-4.1?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 35.9 on the Noometry Index.
Which is cheaper, Gemini 3.8 Flash or GPT-4.1?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-4.1 lists at $2 and $8.
Is Gemini 3.8 Flash or GPT-4.1 better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 3.8 Flash and GPT-4.1 share?
32 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GPT-4.1 has 52.