Model comparison
GPT-5 Nano vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 36× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. GPT-5 Nano scores higher in 2 categories and Nova Premier 1.0 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nova Premier 1.0 leads 51.0 to 39.1.
- The biggest single-benchmark swing is Omni-MATH: 54.6% for GPT-5 Nano and 35% for Nova Premier 1.0.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5 Nano | Nova Premier 1.0 | |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 33.5 | 38.3 |
| Released | 2025-08-07 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 10K |
| Input $ / M tokens | $0.05 | $2.50 |
| Output $ / M tokens | $0.40 | $12.50 |
| Results tracked | 49 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5 Nano: 33.6 (#254), Nova Premier 1.0: —
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| LMArena Coding | 1351 | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Nova Premier 1.0: —
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Nova Premier 1.0 leads
GPT-5 Nano: 16.3 (#306), Nova Premier 1.0: 23.0 (#185)
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 62.2% | 44.8% |
| ARC-AGI-2 | 2.6% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| LMArena Hard Prompts | 1328 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math Nova Premier 1.0 leads
GPT-5 Nano: 29.4 (#241), Nova Premier 1.0: 33.8 (#199)
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 54.6% | 35% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| LMArena Math | 1317 | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GPT-5 Nano: 35.9 (#178), Nova Premier 1.0: 35.8 (#180)
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 77.8% | 72.6% |
| GPQA (HELM) | 67.9% | 51.8% |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 10.5% | — |
| LMArena Expert | 1321 | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Nova Premier 1.0: —
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Not comparable
GPT-5 Nano: 45.3 (#172), Nova Premier 1.0: —
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1356 | — |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1296 | — |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Nova Premier 1.0: 66.8 (#204)
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| IFEval | 93.2% | 80.3% |
| LMArena Instruction Following | 1306 | — |
Long Context Not comparable
GPT-5 Nano: 31.3 (#281), Nova Premier 1.0: —
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1312 | — |
Writing & Preference Nova Premier 1.0 leads
GPT-5 Nano: 39.1 (#249), Nova Premier 1.0: 51.0 (#178)
| Benchmark | GPT-5 Nano | Nova Premier 1.0 |
|---|---|---|
| WildBench | 80.6% | 78.8% |
| LMArena Text | 1320 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 705 | — |
| LMArena Multi-Turn | 1311 | — |
Frequently asked questions
Is GPT-5 Nano better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 36× less per token, which makes it the better buy when Nova Premier 1.0's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or Nova Premier 1.0?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 400K.
How many benchmarks do GPT-5 Nano and Nova Premier 1.0 share?
6 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Nova Premier 1.0 has 6.