Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.8 to 32.1 on the Noometry Index.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 1 category and GPT-5 Mini in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 25.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 86.7% for GPT-5 Mini.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-5 Mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 41.8 |
| Released | 2024-02-15 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 45 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-5 Mini: 40.1 (#146)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| WeirdML | 22.2% | 52.7% |
| LMArena Coding | 1294 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-5 Mini: 31.1 (#70)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-5 Mini: 23.9 (#168)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 4.4% |
| LMArena Hard Prompts | 1296 | 1380 |
| DTBench | 59% | 80.5% |
| Epoch Capabilities Index | 131.73 | 145.52 |
| ForecastBench | 58.4 | 61 |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| Mystery Game Puzzles | — | 10% |
| LMCA | — | 34.2% |
| BIG-Bench Hard | 89.2% | — |
Math GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-5 Mini: 46.7 (#69)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 86.7% |
| Omni-MATH | 36.4% | 72.2% |
| LMArena Math | 1315 | 1378 |
| MATH Level 5 | 70.4% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 9% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-5 Mini: 45.6 (#86)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 57.2% | 75% |
| Humanity's Last Exam | 4.6% | 19.4% |
| MMLU-Pro | 73.7% | 83.5% |
| Confabulations | 13.5% | 13.3% |
| GPQA (HELM) | 53.4% | 75.6% |
| LMArena Expert | 1279 | 1379 |
| SimpleQA Verified | — | 21.6% |
| Vectara Hallucination Rate | — | 12.9% |
| MMLU | 86.9% | — |
Multimodal Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-5 Mini: 35.6 (#85)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1161 | 1202 |
| Video-MME | 75% | — |
| VPCT | — | 40.2% |
Multilingual GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-5 Mini: 48.9 (#137)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1312 | 1363 |
| LMArena Chinese | 1331 | 1385 |
| LMArena French | 1302 | 1386 |
| LMArena German | 1286 | 1366 |
| LMArena Japanese | 1292 | 1341 |
| LMArena Korean | 1298 | 1308 |
| LMArena Russian | 1320 | 1362 |
| LMArena Spanish | 1311 | 1355 |
Instruction Following GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-5 Mini: 76.2 (#46)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| IFEval | 83.7% | 92.7% |
| LMArena Instruction Following | 1297 | 1357 |
Long Context GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-5 Mini: 41.9 (#132)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1308 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GPT-5 Mini leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-5 Mini: 55.2 (#148)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1319 | 1373 |
| LMArena Creative Writing | 1333 | 1325 |
| WildBench | 81.3% | 85.5% |
| LMArena Multi-Turn | 1296 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-5 Mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-5 Mini share?
33 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-5 Mini has 60.