Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-4o mini
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 25.5 on the Noometry Index.
Last verified . 39 shared benchmarks.
GoogleSummary
- They share 39 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 9 categories and GPT-4o mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 1.5 Pro (May 2024) leads 25.8 to 10.4.
- The biggest single-benchmark swing is Confabulations: 13.5% for Gemini 1.5 Pro (May 2024) and 37.2% for GPT-4o mini.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-4o mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 25.5 |
| Released | 2024-02-15 | 2024-07-18 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 45 | 60 |
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-4o mini: 22.0 (#335)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| WeirdML | 22.2% | 11.8% |
| BigCodeBench Instruct | 43.8% | 46.1% |
| LMArena Coding | 1294 | 1290 |
| BigCodeBench Complete | 57.5% | 57.4% |
| HumanEval+ | 79.3% | 83.5% |
| MBPP+ | 74.6% | 72.2% |
| Aider Polyglot | — | 3.6% |
| LiveBench Coding | — | 43.1% |
| CadEval | 34% | — |
Agentic & Tool Use GPT-4o mini leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-4o mini: 27.5 (#101)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| BALROG | 21% | 17.4% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
Reasoning Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-4o mini: 8.7 (#347)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0% |
| SimpleBench | 27.1% | 10.7% |
| LMArena Hard Prompts | 1296 | 1267 |
| DTBench | 59% | 54.4% |
| Epoch Capabilities Index | 131.73 | 126.56 |
| Kagi LLM Benchmark | — | 28.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-4o mini: 10.4 (#314)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 6.9% |
| Omni-MATH | 36.4% | 28% |
| LMArena Math | 1315 | 1267 |
| MATH Level 5 | 70.4% | 52.6% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LiveBench Math | — | 36.3% |
| GSM8K | — | 91.3% |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-4o mini: 17.7 (#284)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 57.2% | 37.7% |
| MMLU-Pro | 73.7% | 60.3% |
| Confabulations | 13.5% | 37.2% |
| GPQA (HELM) | 53.4% | 36.8% |
| LMArena Expert | 1279 | 1235 |
| MMLU | 86.9% | 81.8% |
| Humanity's Last Exam | 4.6% | — |
| SimpleQA Verified | — | 8.3% |
| BoolQ | — | 88.7% |
Multimodal Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-4o mini: 25.9 (#122)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1161 | 1066 |
| Video-MME | 75% | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-4o mini: 42.0 (#199)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1312 | 1266 |
| LMArena Chinese | 1331 | 1265 |
| LMArena French | 1302 | 1297 |
| LMArena German | 1286 | 1272 |
| LMArena Japanese | 1292 | 1216 |
| LMArena Korean | 1298 | 1195 |
| LMArena Russian | 1320 | 1275 |
| LMArena Spanish | 1311 | 1276 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-4o mini: 61.9 (#239)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| IFEval | 83.7% | 78.2% |
| LMArena Instruction Following | 1297 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
Long Context Too close to call
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-4o mini: 39.1 (#186)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1308 | 1289 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-4o mini: 39.5 (#248)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Text | 1319 | 1286 |
| LMArena Creative Writing | 1333 | 1268 |
| WildBench | 81.3% | 79.1% |
| LMArena Multi-Turn | 1296 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-4o mini?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 25.5 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-4o mini better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 22.0 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-4o mini share?
39 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-4o mini has 60.