Model comparison
GPT-5 Mini vs Nova 2 Lite
GPT-5 Mini is the stronger model overall, scoring 41.8 to 39.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GPT-5 Mini scores higher in 7 categories and Nova 2 Lite in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 37.5.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 55.5% for GPT-5 Mini and 27.1% for Nova 2 Lite.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5 Mini | Nova 2 Lite | |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 41.8 | 39.7 |
| Released | 2025-08-07 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.25 | $0.30 |
| Output $ / M tokens | $2 | $2.50 |
| Results tracked | 60 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Mini: 40.1 (#146), Nova 2 Lite: 40.7 (#134)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1406 | 1385 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.1 (#70), Nova 2 Lite: 24.1 (#121)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | 55.5% | 27.1% |
| Terminal-Bench | 34.8% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning Nova 2 Lite leads
GPT-5 Mini: 23.9 (#168), Nova 2 Lite: 27.5 (#118)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1380 | 1364 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Nova 2 Lite: 37.5 (#156)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1378 | 1359 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Nova 2 Lite: 43.0 (#94)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 5.1% |
| LMArena Expert | 1379 | 1358 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Nova 2 Lite: —
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), Nova 2 Lite: 47.1 (#153)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1363 | 1337 |
| LMArena Chinese | 1385 | 1364 |
| LMArena French | 1386 | 1381 |
| LMArena German | 1366 | 1343 |
| LMArena Japanese | 1341 | 1271 |
| LMArena Korean | 1308 | 1284 |
| LMArena Russian | 1362 | 1343 |
| LMArena Spanish | 1355 | 1373 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Nova 2 Lite: 70.5 (#161)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1357 | 1335 |
| IFEval | 92.7% | — |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#132), Nova 2 Lite: 40.6 (#150)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1355 | 1335 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), Nova 2 Lite: 53.9 (#154)
| Benchmark | GPT-5 Mini | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1373 | 1362 |
| LMArena Creative Writing | 1325 | 1291 |
| LMArena Multi-Turn | 1363 | 1338 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Nova 2 Lite?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 39.7 on the Noometry Index.
Which is cheaper, GPT-5 Mini or Nova 2 Lite?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.
Is GPT-5 Mini or Nova 2 Lite better for coding?
They score almost the same on coding (40.1 vs 40.7); test both on your own repository before choosing.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 400K.
How many benchmarks do GPT-5 Mini and Nova 2 Lite share?
19 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Nova 2 Lite has 19.