Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-3.5-turbo
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 23.2 on the Noometry Index.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 7 categories and GPT-3.5-turbo in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 25.3.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 15.9% for GPT-3.5-turbo.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 23.2 |
| Released | 2024-02-15 | 2023-03-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 16K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $1.50 |
| Results tracked | 45 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| WeirdML | 22.2% | 3.5% |
| BigCodeBench Instruct | 43.8% | 39.1% |
| LMArena Coding | 1294 | 1136 |
| BigCodeBench Complete | 57.5% | 50.6% |
| HumanEval+ | 79.3% | 70.7% |
| MBPP+ | 74.6% | 69.7% |
| CadEval | 34% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-3.5-turbo: —
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| METR Time Horizons | — | 21.5% |
Reasoning GPT-3.5-turbo leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1108 |
| DTBench | 59% | 48.5% |
| BIG-Bench Hard | 89.2% | 61.6% |
| Epoch Capabilities Index | 131.73 | 118.55 |
| ForecastBench | 58.4 | 50.4 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Chess Puzzles | — | 0% |
| Mystery Game Puzzles | — | 3% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| CommonsenseQA 2.0 | — | 57% |
| WinoGrande | — | 81.6% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 2.2% |
| LMArena Math | 1315 | 1142 |
| MATH Level 5 | 70.4% | 15.9% |
| FrontierMath (Tiers 1-3) | — | 0% |
| Omni-MATH | 36.4% | — |
| GSM8K | — | 57.8% |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| GPQA Diamond | 57.2% | 28% |
| LMArena Expert | 1279 | 1070 |
| MMLU | 86.9% | 71.4% |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-3.5-turbo: —
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1312 | 1108 |
| LMArena Chinese | 1331 | 1075 |
| LMArena French | 1302 | 1118 |
| LMArena German | 1286 | 1090 |
| LMArena Japanese | 1292 | 1043 |
| LMArena Korean | 1298 | 1019 |
| LMArena Russian | 1320 | 1123 |
| LMArena Spanish | 1311 | 1121 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1297 | 1119 |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1308 | 1121 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1319 | 1125 |
| LMArena Creative Writing | 1333 | 1092 |
| LMArena Multi-Turn | 1296 | 1117 |
| EQ-Bench Creative Writing | — | 451 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-3.5-turbo?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 23.2 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-3.5-turbo better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 23.9 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-3.5-turbo share?
30 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-3.5-turbo has 44.