Model comparison
GPT-5.4 mini vs Nova 2 Lite
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 39.7 on the Noometry Index. Nova 2 Lite costs 2.0× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Nova 2 Lite in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 mini leads 64.0 to 53.9.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Nova 2 Lite accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.4 mini | Nova 2 Lite | |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 45.0 | 39.7 |
| Released | 2026-03-17 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.75 | $0.30 |
| Output $ / M tokens | $4.50 | $2.50 |
| Results tracked | 46 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), Nova 2 Lite: 40.7 (#134)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1438 | 1385 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use GPT-5.4 mini leads
GPT-5.4 mini: 29.9 (#81), Nova 2 Lite: 24.1 (#121)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Nova 2 Lite: 27.5 (#118)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1364 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Nova 2 Lite: 37.5 (#156)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1419 | 1359 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Nova 2 Lite: 43.0 (#94)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 5.1% |
| LMArena Expert | 1435 | 1358 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), Nova 2 Lite: —
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual GPT-5.4 mini leads
GPT-5.4 mini: 51.9 (#96), Nova 2 Lite: 47.1 (#153)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1405 | 1337 |
| LMArena Chinese | 1446 | 1364 |
| LMArena French | 1440 | 1381 |
| LMArena German | 1409 | 1343 |
| LMArena Japanese | 1374 | 1271 |
| LMArena Korean | 1368 | 1284 |
| LMArena Russian | 1417 | 1343 |
| LMArena Spanish | 1405 | 1373 |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.1 (#102), Nova 2 Lite: 70.5 (#161)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1405 | 1335 |
Long Context GPT-5.4 mini leads
GPT-5.4 mini: 43.0 (#112), Nova 2 Lite: 40.6 (#150)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1407 | 1335 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Nova 2 Lite: 53.9 (#154)
| Benchmark | GPT-5.4 mini | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1412 | 1362 |
| LMArena Creative Writing | 1370 | 1291 |
| LMArena Multi-Turn | 1429 | 1338 |
| EQ-Bench Creative Writing | 1665 | — |
Frequently asked questions
Is GPT-5.4 mini better than Nova 2 Lite?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 39.7 on the Noometry Index. Nova 2 Lite costs 2.0× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 mini or Nova 2 Lite?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Nova 2 Lite better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 40.7 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 400K.
How many benchmarks do GPT-5.4 mini and Nova 2 Lite share?
18 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Nova 2 Lite has 19.