Model comparison
Gemini 1.5 Flash (May 2024) vs GPT-5.4 nano
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 32.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 0 categories and GPT-5.4 nano in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 nano leads 40.7 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.3% for Gemini 1.5 Flash (May 2024) and 87.8% for GPT-5.4 nano.
Side by side
| Gemini 1.5 Flash (May 2024) | GPT-5.4 nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.9 | 41.9 |
| Released | 2024-05-14 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.25 |
| Results tracked | 42 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 33.9 (#233), GPT-5.4 nano: 43.1 (#82)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| WeirdML | 24.9% | 49.2% |
| LMArena Coding | 1262 | 1404 |
| SciCode | — | 46.9% |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| ALE-Bench | — | 1,005 |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Flash (May 2024): 26.3 (#97), GPT-5.4 nano: —
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| BALROG | 14.6% | — |
Reasoning GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 20.8 (#212), GPT-5.4 nano: 23.8 (#159)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1380 |
| DTBench | 53.8% | 80.3% |
| Epoch Capabilities Index | 129.37 | 145.78 |
| ForecastBench | 53.9 | 57.3 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| Mystery Game Puzzles | — | 9% |
| LMCA | — | 36.9% |
| PIQA | 87.5% | — |
Math GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 20.8 (#274), GPT-5.4 nano: 40.7 (#76)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 87.8% |
| LMArena Math | 1269 | 1406 |
| FrontierMath (Feb 2025 set) | 0% | 25.9% |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 5% |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |
| GSM8K | 82.4% | — |
Knowledge GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 26.2 (#253), GPT-5.4 nano: 41.8 (#94)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 47.3% | 78.5% |
| LMArena Expert | 1233 | 1397 |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | 67.8% | — |
| Vectara Hallucination Rate | — | 3.1% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal Too close to call
Gemini 1.5 Flash (May 2024): 35.3 (#76), GPT-5.4 nano: 36.0 (#73)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 1141 | 1196 |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 43.1 (#184), GPT-5.4 nano: 48.8 (#136)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1278 | 1359 |
| LMArena Chinese | 1295 | 1391 |
| LMArena French | 1257 | 1396 |
| LMArena German | 1262 | 1368 |
| LMArena Japanese | 1252 | 1342 |
| LMArena Korean | 1220 | 1321 |
| LMArena Russian | 1288 | 1363 |
| LMArena Spanish | 1242 | 1368 |
Instruction Following GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 67.0 (#199), GPT-5.4 nano: 72.1 (#139)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1258 | 1362 |
| IFEval | 83.1% | — |
Long Context GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 39.0 (#182), GPT-5.4 nano: 41.6 (#131)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1284 | 1365 |
Writing & Preference GPT-5.4 nano leads
Gemini 1.5 Flash (May 2024): 48.9 (#190), GPT-5.4 nano: 55.9 (#137)
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1287 | 1372 |
| LMArena Creative Writing | 1285 | 1313 |
| LMArena Multi-Turn | 1253 | 1382 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than GPT-5.4 nano?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 32.9 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 33.9 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and GPT-5.4 nano share?
25 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and GPT-5.4 nano has 40.