Model comparison
Gemini 3.6 Flash vs GPT-4 Turbo
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 30.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and GPT-4 Turbo in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.6 Flash leads 57.3 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.2% for Gemini 3.6 Flash and 6.7% for GPT-4 Turbo.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 128K.
Side by side
| Gemini 3.6 Flash | GPT-4 Turbo | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 30.5 |
| Released | 2026-07-21 | 2023-11-06 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.75 | $10 |
| Output $ / M tokens | $3.75 | $30 |
| Results tracked | 46 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Gemini 3.6 Flash: 50.0 (#48), GPT-4 Turbo: 33.8 (#249)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| WeirdML | 56.1% | 18% |
| LMArena Coding | 1491 | 1268 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| LMArena WebDev | 1538 | — |
| SciCode | 52.7% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| ALE-Bench | 715.52 | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Gemini 3.6 Flash: 32.3 (#65), GPT-4 Turbo: —
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| APEX-Agents | 46.9% | — |
| GDP.pdf | 14% | — |
| METR Time Horizons | — | 36.7% |
Reasoning Gemini 3.6 Flash leads
Gemini 3.6 Flash: 58.8 (#22), GPT-4 Turbo: 15.3 (#317)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| Chess Puzzles | 43% | 6% |
| LMArena Hard Prompts | 1485 | 1251 |
| DTBench | 95.5% | 61.6% |
| LMCA | 44.9% | 9.8% |
| Epoch Capabilities Index | 154.25 | 127.25 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | — | 25.1% |
| NYT Connections (extended) | 89% | — |
| ARC-AGI-1 | 91.2% | — |
| CritPt | 10.6% | — |
| Mystery Game Puzzles | 30% | — |
| ForecastBench | — | 59.4 |
Math Gemini 3.6 Flash leads
Gemini 3.6 Flash: 57.3 (#40), GPT-4 Turbo: 9.0 (#322)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 0.7% |
| OTIS Mock AIME 2024-2025 | 94.2% | 6.7% |
| LMArena Math | 1505 | 1272 |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| ProofBench | 36% | — |
| MATH Level 5 | — | 46.7% |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#8), GPT-4 Turbo: 24.3 (#268)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 94.1% | 46.6% |
| LMArena Expert | 1488 | 1223 |
| SimpleQA Verified | 66.2% | — |
| Confabulations | — | 28.4% |
| MMLU | — | 81.3% |
Multimodal Gemini 3.6 Flash leads
Gemini 3.6 Flash: 38.5 (#64), GPT-4 Turbo: 30.6 (#110)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | 1298 | 1090 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.5 (#19), GPT-4 Turbo: 40.5 (#216)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1469 | 1245 |
| LMArena Chinese | 1531 | 1242 |
| LMArena French | 1504 | 1276 |
| LMArena German | 1478 | 1259 |
| LMArena Japanese | 1476 | 1194 |
| LMArena Korean | 1431 | 1187 |
| LMArena Russian | 1487 | 1259 |
| LMArena Spanish | 1475 | 1260 |
Instruction Following Gemini 3.6 Flash leads
Gemini 3.6 Flash: 77.0 (#33), GPT-4 Turbo: 65.8 (#216)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1466 | 1249 |
Long Context Gemini 3.6 Flash leads
Gemini 3.6 Flash: 45.1 (#50), GPT-4 Turbo: 38.0 (#206)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1474 | 1254 |
Writing & Preference Gemini 3.6 Flash leads
Gemini 3.6 Flash: 68.2 (#27), GPT-4 Turbo: 47.7 (#206)
| Benchmark | Gemini 3.6 Flash | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1479 | 1272 |
| LMArena Creative Writing | 1465 | 1269 |
| LMArena Multi-Turn | 1481 | 1267 |
| EQ-Bench Creative Writing | 1604 | — |
Frequently asked questions
Is Gemini 3.6 Flash better than GPT-4 Turbo?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 30.5 on the Noometry Index.
Which is cheaper, Gemini 3.6 Flash or GPT-4 Turbo?
Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is Gemini 3.6 Flash or GPT-4 Turbo better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.6 Flash does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 3.6 Flash and GPT-4 Turbo share?
26 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-4 Turbo has 36.