Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 32.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and GPT-5.4 mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 29.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 88.9% for GPT-5.4 mini.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 45.0 |
| Released | 2024-02-15 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $4.50 |
| Results tracked | 45 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-5.4 mini: 45.2 (#72)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| WeirdML | 22.2% | 60.3% |
| LMArena Coding | 1294 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-5.4 mini: 29.9 (#81)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 36.3% |
| BALROG | 21% | — |
Reasoning GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-5.4 mini: 30.4 (#85)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 18.9% |
| LMArena Hard Prompts | 1296 | 1424 |
| DTBench | 59% | 80% |
| Epoch Capabilities Index | 131.73 | 148.84 |
| ForecastBench | 58.4 | 57 |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| LMCA | — | 40.8% |
| BIG-Bench Hard | 89.2% | — |
Math GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 88.9% |
| LMArena Math | 1315 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 57.2% | 86.9% |
| LMArena Expert | 1279 | 1435 |
| Humanity's Last Exam | 4.6% | — |
| SimpleQA Verified | — | 29.4% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 5.5% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-5.4 mini: 39.7 (#56)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1161 | 1245 |
| Video-MME | 75% | — |
Multilingual GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-5.4 mini: 51.9 (#96)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1312 | 1405 |
| LMArena Chinese | 1331 | 1446 |
| LMArena French | 1302 | 1440 |
| LMArena German | 1286 | 1409 |
| LMArena Japanese | 1292 | 1374 |
| LMArena Korean | 1298 | 1368 |
| LMArena Russian | 1320 | 1417 |
| LMArena Spanish | 1311 | 1405 |
Instruction Following GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1297 | 1405 |
| IFEval | 83.7% | — |
Long Context GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1308 | 1407 |
Writing & Preference GPT-5.4 mini leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1319 | 1412 |
| LMArena Creative Writing | 1333 | 1370 |
| LMArena Multi-Turn | 1296 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-5.4 mini share?
25 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-5.4 mini has 46.