Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 35.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and GPT-5.4 mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 32.0.
- The biggest single-benchmark swing is WeirdML: 25.8% for Gemini 2.0 Flash (Feb 2025) and 60.3% for GPT-5.4 mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 45.0 |
| Released | 2024-12-06 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $4.50 |
| Results tracked | 54 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-5.4 mini: 45.2 (#72)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| WeirdML | 25.8% | 60.3% |
| LMArena Coding | 1350 | 1438 |
| FrontierCode | — | 27% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-5.4 mini: 29.9 (#81)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| TheAgentCompany | 11.4% | — |
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-5.4 mini: 30.4 (#85)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 18.9% |
| Kagi LLM Benchmark | 37.8% | 37.9% |
| LMArena Hard Prompts | 1346 | 1424 |
| DTBench | 63.2% | 80% |
| Epoch Capabilities Index | 135.36 | 148.84 |
| SimpleBench | 31.1% | — |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| EnigmaEval | 1.1% | — |
| Thematic Generalization | — | 61.7% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 11% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 40.8% |
| ForecastBench | — | 57 |
| LiveBench | 66.9% | — |
Math GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 88.9% |
| LMArena Math | 1352 | 1419 |
| FrontierMath (Feb 2025 set) | 1.7% | 28.3% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 64.1% | 86.9% |
| LMArena Expert | 1339 | 1435 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 29.4% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 5.5% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-5.4 mini: 39.7 (#56)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1158 | 1245 |
| GeoBench | 77% | — |
Multilingual GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-5.4 mini: 51.9 (#96)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1342 | 1405 |
| LMArena Chinese | 1373 | 1446 |
| LMArena French | 1391 | 1440 |
| LMArena German | 1353 | 1409 |
| LMArena Japanese | 1294 | 1374 |
| LMArena Korean | 1313 | 1368 |
| LMArena Russian | 1351 | 1417 |
| LMArena Spanish | 1363 | 1405 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1336 | 1405 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1344 | 1407 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference GPT-5.4 mini leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1354 | 1412 |
| LMArena Creative Writing | 1340 | 1370 |
| EQ-Bench Creative Writing | 1128 | 1665 |
| LMArena Multi-Turn | 1350 | 1429 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-5.4 mini share?
27 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-5.4 mini has 46.