Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-5.4 nano
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 35.1 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and GPT-5.4 nano in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.4 nano leads 43.6 to 28.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 87.8% for GPT-5.4 nano.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 41.9 |
| Released | 2024-12-06 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.25 |
| Results tracked | 54 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-5.4 nano: 43.6 (#84)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| WeirdML | 25.8% | 49.2% |
| LMArena Coding | 1350 | 1405 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| SciCode | — | 46.9% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 1,005 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-5.4 nano: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-5.4 nano: 23.7 (#173)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| ARC-AGI-2 | 1.3% | 5.7% |
| Kagi LLM Benchmark | 37.8% | 39.7% |
| LMArena Hard Prompts | 1346 | 1381 |
| DTBench | 63.2% | 80.3% |
| Epoch Capabilities Index | 135.36 | 145.81 |
| SimpleBench | 31.1% | — |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 36.9% |
| ForecastBench | — | 57.3 |
| LiveBench | 66.9% | — |
Math GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-5.4 nano: 40.9 (#88)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 87.8% |
| LMArena Math | 1352 | 1406 |
| FrontierMath (Feb 2025 set) | 1.7% | 25.9% |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 5% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-5.4 nano: 41.9 (#103)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 64.1% | 78.5% |
| LMArena Expert | 1339 | 1396 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 3.1% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Too close to call
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-5.4 nano: 36.7 (#78)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 1158 | 1196 |
| GeoBench | 77% | — |
Multilingual GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-5.4 nano: 48.6 (#140)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1342 | 1359 |
| LMArena Chinese | 1373 | 1392 |
| LMArena French | 1391 | 1396 |
| LMArena German | 1353 | 1367 |
| LMArena Japanese | 1294 | 1343 |
| LMArena Korean | 1313 | 1320 |
| LMArena Russian | 1351 | 1363 |
| LMArena Spanish | 1363 | 1371 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-5.4 nano: 71.9 (#144)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1336 | 1362 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-5.4 nano: 41.6 (#137)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1344 | 1366 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference GPT-5.4 nano leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-5.4 nano: 55.7 (#142)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1354 | 1372 |
| LMArena Creative Writing | 1340 | 1314 |
| LMArena Multi-Turn | 1350 | 1382 |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-5.4 nano?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-5.4 nano share?
26 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-5.4 nano has 40.