Model comparison
Nova Premier 1.0 vs o3
o3 is the stronger model overall, scoring 47.5 to 38.3 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. Nova Premier 1.0 scores higher in 0 categories and o3 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 35.8.
- The biggest single-benchmark swing is Omni-MATH: 35% for Nova Premier 1.0 and 71.4% for o3.
- o3 is cheaper at $2 / $8 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 200K.
Side by side
| Nova Premier 1.0 | o3 | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 38.3 | 47.5 |
| Released | 2025-04-30 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 10K | 100K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $12.50 | $8 |
| Results tracked | 6 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nova Premier 1.0: —, o3: 46.8 (#64)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| LMArena Coding | — | 1408 |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Nova Premier 1.0: —, o3: 34.5 (#44)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Nova Premier 1.0: 23.0 (#185), o3: 32.0 (#78)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| Kagi LLM Benchmark | 44.8% | 67.6% |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| LMArena Hard Prompts | — | 1402 |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
Nova Premier 1.0: 33.8 (#199), o3: 50.2 (#58)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| Omni-MATH | 35% | 71.4% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| LMArena Math | — | 1426 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Nova Premier 1.0: 35.8 (#180), o3: 54.6 (#52)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| MMLU-Pro | 72.6% | 85.9% |
| GPQA (HELM) | 51.8% | 75.3% |
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| Confabulations | — | 14.4% |
| LMArena Expert | — | 1402 |
Multimodal Not comparable
Nova Premier 1.0: —, o3: 41.4 (#36)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Not comparable
Nova Premier 1.0: —, o3: 51.7 (#105)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| LMArena Non-English | — | 1401 |
| LMArena Chinese | — | 1437 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1395 |
Instruction Following o3 leads
Nova Premier 1.0: 66.8 (#204), o3: 72.8 (#127)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| IFEval | 80.3% | 86.9% |
| LMArena Instruction Following | — | 1368 |
Long Context Not comparable
Nova Premier 1.0: —, o3: 53.3 (#6)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
| LMArena Longer Query | — | 1372 |
Writing & Preference o3 leads
Nova Premier 1.0: 51.0 (#178), o3: 63.5 (#64)
| Benchmark | Nova Premier 1.0 | o3 |
|---|---|---|
| WildBench | 78.8% | 86.1% |
| LMArena Text | — | 1410 |
| LMArena Creative Writing | — | 1359 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Nova Premier 1.0 better than o3?
o3 is the stronger model overall, scoring 47.5 to 38.3 on the Noometry Index.
Which is cheaper, Nova Premier 1.0 or o3?
o3 is cheaper. It lists at $2 per million input tokens and $8 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 200K.
How many benchmarks do Nova Premier 1.0 and o3 share?
6 benchmarks have published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and o3 has 63.