Model comparison
Gemini 2.5 Flash vs GPT-5 Nano
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 6.2× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
GoogleSummary
- They share 41 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 10 categories and GPT-5 Nano in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Flash leads 47.5 to 31.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 77.8% for Gemini 2.5 Flash and 44.4% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 2.5 Flash | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.3 | 33.5 |
| Released | 2025-04-17 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $0.05 |
| Output $ / M tokens | $2.50 | $0.40 |
| Results tracked | 54 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Gemini 2.5 Flash: 35.8 (#220), GPT-5 Nano: 33.6 (#254)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 34.8% |
| WeirdML | 41.9% | 38.1% |
| LMArena Coding | 1424 | 1351 |
| ALE-Bench | 661.88 | 718.67 |
| Aider Polyglot | 55.1% | — |
Agentic & Tool Use Gemini 2.5 Flash leads
Gemini 2.5 Flash: 30.8 (#74), GPT-5 Nano: 25.8 (#106)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | 17.1% | 21.8% |
| Berkeley Function Calling Leaderboard | 56.2% | 51.5% |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.1 (#286), GPT-5 Nano: 16.3 (#306)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| ARC-AGI-2 | 2.5% | 2.6% |
| Kagi LLM Benchmark | 56.8% | 62.2% |
| ARC-AGI-1 | 33.3% | 20.7% |
| LMArena Hard Prompts | 1422 | 1328 |
| DTBench | 76.5% | 62.7% |
| LMCA | 27.5% | 7.9% |
| Epoch Capabilities Index | 143.03 | 139.38 |
| ForecastBench | 60.6 | 59.1 |
| SimpleBench | 41.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 27% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 9% |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), GPT-5 Nano: 29.4 (#241)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 81.1% |
| Omni-MATH | 38.5% | 54.6% |
| LMArena Math | 1415 | 1317 |
| FrontierMath (Feb 2025 set) | 4.8% | 8.3% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 12% |
| MATH Level 5 | — | 95.2% |
Knowledge Too close to call
Gemini 2.5 Flash: 36.4 (#168), GPT-5 Nano: 35.9 (#178)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| MMLU-Pro | 63.9% | 77.8% |
| Vectara Hallucination Rate | 7.8% | 10.5% |
| GPQA (HELM) | 39% | 67.9% |
| LMArena Expert | 1426 | 1321 |
| GPQA Diamond | — | 69.4% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 11.7% |
| Confabulations | 16.8% | — |
Multimodal Gemini 2.5 Flash leads
Gemini 2.5 Flash: 41.8 (#32), GPT-5 Nano: 31.3 (#108)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1253 | 1159 |
| VPCT | 46.2% | 37.2% |
| GeoBench | 76% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), GPT-5 Nano: 45.3 (#172)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1409 | 1313 |
| LMArena Chinese | 1450 | 1356 |
| LMArena German | 1418 | 1327 |
| LMArena Japanese | 1405 | 1226 |
| LMArena Korean | 1385 | 1269 |
| LMArena Russian | 1415 | 1296 |
| LMArena Spanish | 1421 | 1360 |
| LMArena French | 1433 | — |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.7 (#54), GPT-5 Nano: 75.0 (#79)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| IFEval | 89.8% | 93.2% |
| LMArena Instruction Following | 1405 | 1306 |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), GPT-5 Nano: 31.3 (#281)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| Fiction.LiveBench | 77.8% | 44.4% |
| LMArena Longer Query | 1419 | 1312 |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 53.8 (#157), GPT-5 Nano: 39.1 (#249)
| Benchmark | Gemini 2.5 Flash | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1417 | 1320 |
| LMArena Creative Writing | 1400 | 1249 |
| EQ-Bench Creative Writing | 1137 | 705 |
| WildBench | 81.7% | 80.6% |
| LMArena Multi-Turn | 1408 | 1311 |
| Short-Story Creative Writing | 76.5% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than GPT-5 Nano?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 6.2× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or GPT-5 Nano?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or GPT-5 Nano better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 2.5 Flash and GPT-5 Nano share?
41 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GPT-5 Nano has 49.