Model comparison
Gemini 2.5 Pro vs GPT-5.4 nano
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.9 on the Noometry Index. GPT-5.4 nano costs 7.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
GoogleSummary
- They share 37 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and GPT-5.4 nano in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 41.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 70.3% for Gemini 2.5 Pro and 39.7% for GPT-5.4 nano.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 2.5 Pro | GPT-5.4 nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 45.0 | 41.9 |
| Released | 2025-03-25 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $1.25 | $0.20 |
| Output $ / M tokens | $10 | $1.25 |
| Results tracked | 78 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
Gemini 2.5 Pro: 42.4 (#101), GPT-5.4 nano: 43.6 (#84)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| SciCode | 42.8% | 46.9% |
| WeirdML | 54% | 49.2% |
| LMArena Coding | 1452 | 1405 |
| ALE-Bench | 785.52 | 1,005 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| GSO | 3.9% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Pro: 29.2 (#88), GPT-5.4 nano: —
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Gemini 2.5 Pro leads
Gemini 2.5 Pro: 28.8 (#99), GPT-5.4 nano: 23.7 (#173)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| ARC-AGI-2 | 4.9% | 5.7% |
| Kagi LLM Benchmark | 70.3% | 39.7% |
| ARC-AGI-1 | 41% | 51.5% |
| CritPt | 2% | 9.3% |
| Chess Puzzles | 20% | 30% |
| LMArena Hard Prompts | 1455 | 1381 |
| DTBench | 82.4% | 80.3% |
| LMCA | 34.8% | 36.9% |
| Epoch Capabilities Index | 145.32 | 145.81 |
| ForecastBench | 61.3 | 57.3 |
| SimpleBench | 62.4% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 79.9% | — |
| LiveBench | 82.3% | — |
Math GPT-5.4 nano leads
Gemini 2.5 Pro: 32.5 (#213), GPT-5.4 nano: 40.9 (#88)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 44.9% |
| FrontierMath Tier 4 | 0% | 12.2% |
| OTIS Mock AIME 2024-2025 | 84.7% | 87.8% |
| LMArena Math | 1450 | 1406 |
| FrontierMath (Feb 2025 set) | 14.1% | 25.9% |
| FrontierMath Tier 4 (v1) | 4.2% | 6.3% |
| ProofBench | — | 5% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 56.0 (#46), GPT-5.4 nano: 41.9 (#103)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 85.3% | 78.5% |
| Vectara Hallucination Rate | 7% | 3.1% |
| LMArena Expert | 1452 | 1396 |
| Humanity's Last Exam | 21.6% | — |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal Gemini 2.5 Pro leads
Gemini 2.5 Pro: 45.2 (#18), GPT-5.4 nano: 36.7 (#78)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 1263 | 1196 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.3 (#31), GPT-5.4 nano: 48.6 (#140)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1451 | 1359 |
| LMArena Chinese | 1507 | 1392 |
| LMArena French | 1472 | 1396 |
| LMArena German | 1487 | 1367 |
| LMArena Japanese | 1461 | 1343 |
| LMArena Korean | 1434 | 1320 |
| LMArena Russian | 1461 | 1363 |
| LMArena Spanish | 1473 | 1371 |
Instruction Following Gemini 2.5 Pro leads
Gemini 2.5 Pro: 75.0 (#75), GPT-5.4 nano: 71.9 (#144)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1437 | 1362 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), GPT-5.4 nano: 41.6 (#137)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1449 | 1366 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.7 (#62), GPT-5.4 nano: 55.7 (#142)
| Benchmark | Gemini 2.5 Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1458 | 1372 |
| LMArena Creative Writing | 1454 | 1314 |
| LMArena Multi-Turn | 1453 | 1382 |
| Short-Story Creative Writing | 83.8% | — |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than GPT-5.4 nano?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.9 on the Noometry Index. GPT-5.4 nano costs 7.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Pro or GPT-5.4 nano?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Gemini 2.5 Pro or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 2.5 Pro and GPT-5.4 nano share?
37 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GPT-5.4 nano has 40.