Model comparison
GPT-5 Nano vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 33.5 on the Noometry Index. GPT-5 Nano costs 255× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Summary
- They share 9 benchmarks with published results for both. GPT-5 Nano scores higher in 1 category and o3-pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 31.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for GPT-5 Nano and 97.2% for o3-pro.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $20 / $80 for o3-pro.
- GPT-5 Nano accepts more context: 400K tokens versus 200K.
Side by side
| GPT-5 Nano | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.5 | 42.9 |
| Released | 2025-08-07 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.05 | $20 |
| Output $ / M tokens | $0.40 | $80 |
| Results tracked | 49 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
GPT-5 Nano: 33.6 (#254), o3-pro: 55.5 (#24)
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| WeirdML | 38.1% | 58.2% |
| SWE-bench Verified (bash only) | 34.8% | — |
| Aider Polyglot | — | 84.9% |
| LMArena Coding | 1351 | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), o3-pro: —
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning o3-pro leads
GPT-5 Nano: 16.3 (#306), o3-pro: 23.8 (#171)
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| ARC-AGI-2 | 2.6% | 4.9% |
| Kagi LLM Benchmark | 62.2% | 72.1% |
| ARC-AGI-1 | 20.7% | 59.3% |
| DTBench | 62.7% | 86.9% |
| LMCA | 7.9% | 38.5% |
| Epoch Capabilities Index | 139.38 | 147.42 |
| Chess Puzzles | 27% | — |
| LMArena Hard Prompts | 1328 | — |
| Mystery Game Puzzles | 9% | — |
| ForecastBench | 59.1 | — |
Math Not comparable
GPT-5 Nano: 29.4 (#241), o3-pro: —
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LMArena Math | 1317 | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), o3-pro: 29.5 (#238)
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 10.5% | 23.3% |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Confabulations | — | 14.2% |
| GPQA (HELM) | 67.9% | — |
| LMArena Expert | 1321 | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), o3-pro: —
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Not comparable
GPT-5 Nano: 45.3 (#172), o3-pro: —
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1356 | — |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1296 | — |
| LMArena Spanish | 1360 | — |
Instruction Following Not comparable
GPT-5 Nano: 75.0 (#79), o3-pro: —
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| IFEval | 93.2% | — |
| LMArena Instruction Following | 1306 | — |
Long Context o3-pro leads
GPT-5 Nano: 31.3 (#281), o3-pro: 72.2 (#1)
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| Fiction.LiveBench | 44.4% | 97.2% |
| LMArena Longer Query | 1312 | — |
Writing & Preference o3-pro leads
GPT-5 Nano: 39.1 (#249), o3-pro: 57.1 (#133)
| Benchmark | GPT-5 Nano | o3-pro |
|---|---|---|
| LMArena Text | 1320 | — |
| LMArena Creative Writing | 1249 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| LMArena Multi-Turn | 1311 | — |
Frequently asked questions
Is GPT-5 Nano better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 33.5 on the Noometry Index. GPT-5 Nano costs 255× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or o3-pro?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; o3-pro lists at $20 and $80.
Is GPT-5 Nano or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 200K.
How many benchmarks do GPT-5 Nano and o3-pro share?
9 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and o3-pro has 12.