Model comparison
Mercury 2 vs Nova 2 Lite
Mercury 2 and Nova 2 Lite score almost the same on the Noometry Index (38.8 vs 39.0), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Nova 2 Lite in 7 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nova 2 Lite leads 40.1 to 33.2.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.3% for Mercury 2 and 5.1% for Nova 2 Lite.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 128K.
Side by side
| Mercury 2 | Nova 2 Lite | |
|---|---|---|
| Provider | Inception | Amazon |
| Noometry Index | 38.8 | 39.0 |
| Released | 2026-02-20 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 50K | 64K |
| Input $ / M tokens | $0.25 | $0.30 |
| Output $ / M tokens | $0.75 | $2.50 |
| Results tracked | 17 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Mercury 2: 33.2 (#250), Nova 2 Lite: 40.1 (#131)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1391 | 1386 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Nova 2 Lite: 23.9 (#114)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Nova 2 Lite leads
Mercury 2: 23.0 (#170), Nova 2 Lite: 26.4 (#120)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1364 |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, Nova 2 Lite: 34.8 (#154)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Math | — | 1359 |
Knowledge Nova 2 Lite leads
Mercury 2: 35.6 (#170), Nova 2 Lite: 42.5 (#88)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 5.1% |
| LMArena Expert | 1358 | 1360 |
Multilingual Too close to call
Mercury 2: 46.8 (#153), Nova 2 Lite: 47.3 (#148)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1331 | 1337 |
| LMArena Chinese | 1416 | 1364 |
| LMArena Russian | 1303 | 1343 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1273 |
| LMArena Korean | — | 1284 |
| LMArena Spanish | — | 1372 |
Instruction Following Too close to call
Mercury 2: 70.4 (#161), Nova 2 Lite: 70.7 (#156)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1328 | 1335 |
Long Context Too close to call
Mercury 2: 40.4 (#149), Nova 2 Lite: 40.6 (#145)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1329 | 1335 |
Writing & Preference Too close to call
Mercury 2: 54.0 (#151), Nova 2 Lite: 54.1 (#150)
| Benchmark | Mercury 2 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1355 | 1362 |
| LMArena Creative Writing | 1289 | 1291 |
| LMArena Multi-Turn | 1358 | 1338 |
Frequently asked questions
Is Mercury 2 better than Nova 2 Lite?
Mercury 2 and Nova 2 Lite score almost the same on the Noometry Index (38.8 vs 39.0), so choose on price, context window or the category you care about most.
Which is cheaper, Mercury 2 or Nova 2 Lite?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.
Is Mercury 2 or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 128K.
How many benchmarks do Mercury 2 and Nova 2 Lite share?
12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Nova 2 Lite has 19.